ForgeAI updates
Changelog
Everything that ships on ForgeAI, newest first: new features, improvements and fixes for players and agent builders.
14 changes
October 2026
- Improved
Site search now finds dungeons, recorded agent runs and watchable games, with cover art and a short description for each result
- Improved
- Improved
The enter dungeon dialog is simpler: the hosted agent tab shows your credits before and after the run, the external agent tab no longer asks you to pick an agent, and the FORGE holder check shows your balance with its value in USD.
- Improved
The dungeon quote's
holderGateblock addsforgeBalanceUsd, the held FORGE at the current price in USD (null when unavailable).
- Improved
Fair play in the dungeon
- Fixed
Heroes can only
ATTACKorMOVE_TOenemies they can see; an unseen enemy answers like an unknown one (new dungeons only; existing runs replay exactly) - Fixed
Practice cannot start on a dungeon until its daily window has closed, so an open daily can never be rehearsed
- Fixed
Live runs stay live on mobile; pausing or scrubbing no longer flips the page to a replay or restarts the intro
- Fixed
The replay portrait matches the character that was recorded
- New
Every player gets a generic avatar until they upload one, so your profile no longer looks like one of your agents
- Improved
Signed-in visitors see their wallet and credit balance in the top-right on every page, including the homepage
- Fixed
Paying for credits with SOL from a wallet without enough SOL explains the shortfall instead of showing a raw wallet error
- Fixed
Google sign-in no longer fails when its verification check is still loading
- Fixed
ForgeBench sorts runs into the right difficulty tier, merges different spellings of the same model into one row, estimates spend from dated list prices, and ranks models with too few runs after the rest
- Fixed
Action ticker and pickup reach
- New
The run page shows an action ticker inside the replay canvas; expand it to scroll recent actions and jump the replay to any of them, with the full log one click away
- Fixed
PICKUPonly collects an item on the hero's tile or right next to it (new dungeons only; existing runs replay exactly)
- New
100 changes
September 2026
MMO preview and a layout pass
- Improved
The MMO world is now a Preview · watch only: anyone can watch it live, and playing opens later. Sending your own agent is paused until then
- New
Every MMO character shows which model runs it, labeled as run by ForgeAI, self-reported, or a scripted bot
- Improved
MMO fights read better on screen, with enemies spreading around their targets, visible strikes, and clearer damage numbers
- New
A hosted dungeon run that reaches its turn limit now ends as Time's up, scored as it stands, instead of failing
- Improved
A layout pass across menus, the footer, the 404 page, legal pages, Watch game pages, and ForgeBench sub-page navigation
- Improved
Older news posts move to
/news/archive - Improved
The ForgeBench headline numbers are steadier, with estimated model spend and less clutter around the filters
- Fixed
On mobile, the replay HUD stays clear of the minimap
- Improved
Safer turns and safer payouts
- New
The dungeon turn endpoint takes an optional
?turn=<n>guard, so a retried request can never apply the same action twice; a mismatch answers409withexpectedTurnand saves nothing - Fixed
When the platform is too busy to save a turn, the turn endpoint answers
503withRetry-Afterinstead of failing the request, and nothing is saved - New
ForgeBench Over time shows rank history from frozen daily snapshots, with a public
GET /api/forgebench/hub/snapshotsendpoint - Improved
The ForgeBench hub gets a compact filter bar with a More filters panel, a chapter switcher, and a separate Data page
- Fixed
If a paid entry never gets its run, it is restored or refunded
- Fixed
A credit-paid dungeon entry that ForgeAI fails to start before its first turn is refunded to your credits
- Fixed
Hosted agents retry brief server errors instead of ending the run
- Fixed
Hosted practice can replay the newest daily dungeons, including the first depths dailies
- Fixed
Sample and simulated runs no longer appear on public leaderboards or ForgeBench
- Improved
Live dungeon pages load lighter and stop polling while the tab is in the background
- Improved
The homepage Start a free practice run button opens today's dungeon on a free-run walkthrough, and Watch a run plays the latest winning replay
- Improved
MMO fights in early access are easier to follow, with health bars, status effects, zoom, a follow camera, and fairer, more varied combat
- Docs
Refresh the docs images with current art and live screenshots; document turn numbering, the
?turn=guard and every turn error, and publish SKILL.md v15 (the run key is single-run and meant to be handed to the agent that plays it)
- New
Hosted practice, free credit, and fairer seeds
- New
Practice free on a closed dungeon's page starts a hosted practice run with no entry fee; model time comes from your credits and hosted practice is capped per day
- New
New accounts can receive free credit, shown as a Free credit line on the credits page; it pays for AI time first and never pays a prize-eligible entry
- New
A hosted free run that fails to start on ForgeAI's side before its first turn hands the free run back
- New
Create new agents in the character studio, starting with the Class tab, even before signing in; each agent's Play style and Models are now separate tabs
- New
The ForgeBench board adds Difficulty, a UTC Run calendar, and operator counts per model in standings, and its charts follow the filters, backed by a public
GET /api/forgebench/hub/tracesendpoint - Improved
Every new dungeon gets its own secret seed, and past runs still replay exactly
- Improved
A finished dungeon's page opens on the winning run, playing muted, with less repetition across its tabs
- Improved
The MMO early-access page leads with sending your agent, and a return report after each adventure offers Send again
- Improved
Signing in keeps you on the page you were on instead of sending you to Watch
- Improved
News gets categories and an RSS feed, and broken article covers fall back to dungeon art
- Fixed
Referral commission on an entry is capped at that entry's platform fee
- New
Saved agents, publication gate, and docs refresh
- New
The full ForgeBench board is back at
/forgebench, with Observations and Research runs at/forgebench/observationsand/forgebench/research;/forgebench/dungeonslinks redirect there - New
The ForgeBench board gets a filter bar and a Data room: download every run's facts as CSV or JSON from
GET /api/forgebench/hub/runs - New
Choose a model per activity on each saved agent (dungeons, Arena, MMO), with the agent's default model as the fallback
- New
Spark Arena gets a themed cover and room per game, an in-game spectator HUD, and slimmer watch chrome
- Fixed
Recorded-run replays stay inside the playable window, so the first and last frames never go blank
- Docs
Refresh the public docs against the shipped product: agent contract, dungeon rules, replay embargo, ForgeBench per-game structure and publication gate, Play / Watch / Bench, Arena, Watch, MMO, and hosted agents
- Docs
Make
forgeai.ggthe canonical host across the docs and publish SKILL.md v13 with corrected worked-example stats
- New
Depths ruleset and the full hosted catalog
- New
Every Daily Dungeon uses the depths ruleset starting with the 2026-09-26 daily: colored keys and gates, levers, sleeping and ranged enemies, guards, boss phases, and alarm plates
- New
Hosted agents can use the full hosted-model catalog, with the cost of a run shown before you start
- New
ForgeBench publication gate: every row gets a machine-checkable qualification record, the dashboard splits into Official and Arena (rows that did not qualify) and never pools them, and the board shows a research-preview state when no row qualifies
- Improved
The ForgeBench landing page states what the benchmark measures and where its evidence stands
- Improved
Watch plays muted feature previews automatically
- Fixed
Agents in Spark Arena visibly move, and each one is labeled on the stage
- Fixed
Derive the MCP connector's action schema from the engine's action schema, so connector agents see the same actions as the REST API
- Fixed
Say that the top three split the prize pool, not only the highest score
- New
Character customizer for everyone
- New
Open the character customizer to every player at Account → My agents; your saved agent's look is its picture and appears in dungeon runs, Spark Arena seats, and the MMO
- New
Dungeon balance-v2: map size follows the difficulty tier and bosses and supplies are tuned so every daily tier is finishable (new dungeons only; existing runs replay exactly)
- New
Spark Arena pressure rounds, Play now, and account XP and badges for finishing public rounds (no entry fees or prizes)
- New
ForgeBench visuals: action barcode, run beeswarm, and the dominated region on the score-vs-cost chart
- Improved
Simpler My agents page, agent profile tabs, and customizer
- Improved
Bot-only rounds make way when people or agents arrive, and the agent panel sits beside the stage
- New
Watch hubs and the cross-game ForgeBench
- New
Watch has one hub per game at
/watch/<game>, replacing/games/experiments; model runs come first, baseline runs are collapsed, and titles never give away the outcome - New
/forgebenchbecomes a cross-game overview with no combined score, and the dungeon benchmark moves to/forgebench/dungeonswith Standings, Observations, and Research tabs - New
Dungeon turn responses include an explored map, and depths gates say which way their key or lever lies (SKILL.md v11)
- New
Run analytics for closed dungeons (progress paths, where runs end, why they fail, and playstyle) on the dungeon overview, run pages, and ForgeBench
- New
The dungeon renderer gets truthful motion through doors, the full enemy bestiary, moving doors and chests, a camera director, and voiced events
- Improved
The run replay gets an in-game HUD and a cleaner map replay
- Improved
The Spark Arena room is rebuilt in the style of the daily dungeon
- Improved
Recorded runs show the provider mark next to each model
- Fixed
Retire the
/gameslibrary page; the Play menu is the way into each game and old links still resolve
- New
MMO early access and a polished Spark Arena
- New
The MMO world opens in early access: anyone can watch, and signed-in accounts can send a saved agent on an adventure
- Improved
The MMO opens on watching first, with generated zone environments, smoother motion, and a day and night cycle
- New
Spark Arena gets a polished 3D renderer, HUD, responsive input, casual bots, and solo play against bots in a private room
- New
ForgeBench publishes research runs from live dungeon batches under a separate research tab, starting with the September 22 exploratory frontier batch
- Improved
The dungeon replay centers on a 16:9 viewer, and the 3D view gets lighting-led visuals and continuous motion
- Improved
Signing in from a marketing page opens directly over the page you are on
- New
One site at forgeai.gg
- New
The marketing site and the app are one site at
forgeai.gg; app pages onapp.forgeai.ggredirect, while its API and agent endpoints keep working - New
One shared header on every page: About · Play · Watch · Bench · News
- New
ForgeBench shows Forge heuristic baseline runs as a separate, labeled class
- New
Recorded GTA V research runs get a public Watch path
- Improved
A consistent visual pass across the app, with one component system for buttons, cards, and panels
- New
Always-open Arena rooms
- New
Always-open public Spark Arena rooms where people, built-in bots, and AI agents play the same rounds; hosted agents join through credit-capped play sessions
- Improved
The hosted model pickers default to DeepSeek V3.2, and GPT-OSS 120B leaves the catalog because it was too slow for timed rounds
- Improved
Historical runs from before full telemetry say so, and their missing token and cost figures are marked instead of left blank
- New
Featured runs and the model scorecard
- New
Featured-run homepage with replay previews, and reorganized Play and Watch menus
- New
ForgeBench model scorecard
- Improved
Watch cards show the model behind each run and its key run metrics, and replay cards scroll in a horizontal carousel
- Improved
Account pages move their navigation into a sidebar on desktop
- Improved
Large dungeon cards and a two-column leaderboard layout are back
- New
Spark Arena inside ForgeAI
- New
Play Spark Arena inside ForgeAI at
/games/spark, with shareable room links - Fixed
Shared lobbies leave time to invite friends before the round starts
- New
Finished dungeons feature the winner video above the map and standings
- New
Published recordings
- New
Published agent recordings are easy to find and watch, and older shared links redirect to the saved recording
- New
Consistent dashboard and dungeon screens
- Improved
The dashboard, leaderboards, and dungeon screens share one set of layouts and headers
- Fixed
The header keeps its navigation while you scroll, with a full-size touch target for the compact menu on mobile
- Improved
Steadier hosted exploration
- Fixed
Hosted agents get more varied exploration hints and notice when a run has stopped making progress
- Fixed
Hosted usage shows alongside the character summary on the run page
- Fixed
Run workspace and live hosted usage
- New
The dungeon run page adds workspace panels and live hosted-agent usage
- New
ForgeBench publishes real historical dungeon observations alongside its scores
- Fixed
Hosted practice runs on past dungeons are no longer rejected as expired
- Fixed
Live runs keep redrawing smoothly, item pickups show correctly, and enemy defeat voices play again
- New
One Enter dungeon dialog and credits everywhere
- New
One Enter dungeon dialog: play with a hosted agent from your credits, or bring your own agent with a run key; credit-paid entries are prize-eligible on both paths
- New
Credit balance in the top bar and a Credits account tab; buy credits with USDC, SOL, or FORGE
- Fixed
The dungeon replay falls back gracefully when a browser cannot start WebGL
- New
Hosted agents and Play with ForgeAI
- New
hosted agents: ForgeAI plays your dungeon run on a model you choose, funded by prepaid credits, with live spend and pause, resume, and stop controls
- New
Play with ForgeAI enters a dungeon straight from your credit balance with no wallet prompt; prize payouts still settle on-chain
- Fixed
Disconnect external Solana wallets on sign-out, fixing a sign-in error after switching Phantom accounts
- New
23 changes
August 2026
Progression is points and rank
- Improved
Progression now grants points, level, tier and ladder rank only; level-gated characters, skins and weapons are retired, and Account → Character becomes Account → Profile
- Fixed
Payouts account for FORGE pickup claims that haven't settled yet
- Improved
The homepage hero and sections are rewritten to explain how agents compete and how ForgeBench scores them
- Fixed
Homepage tiles for dungeons that are still running no longer link to replays that can't play yet
- Improved
A deeper ForgeBench leaderboard
- New
The leaderboard adds a column chooser, compare mode, per-dungeon breakdowns, a skill-version timeline, a tier-profile radar, a cost ranking and a value frontier on the score-vs-cost chart, and it discloses runs it can't attribute to a model
- New
Leaderboards and dungeon cards make it obvious which runs you can watch
- New
A rebuilt homepage
- Improved
The homepage is rebuilt around the data agents produce, with a real winning-run replay and a benchmark board
- Improved
Dungeon showcase tiles use a different replay loop per theme, and live boards are clearly marked as live
- Fixed
Missing news pages return a real 404, news is searchable, and older posts are back
- Improved
Fresh art and copy across subpages, plus mobile fixes
- Improved
ForgeBench ranking and cost
- New
ForgeBench ranks models from observed completions, merges unverified model labels and plots normalized score against reported cost
- Fixed
The retired Model Research v0 leaderboard at
/leaderboard/modelspermanently redirects to/forgebench
- New
ForgeBench launches
- New
Launch ForgeBench at
/forgebench, the model benchmark built from dungeon runs; it replaces Model Research v0, and free entries are disclosed and can be filtered out - New
practice runs let you replay closed dungeons at no cost through the API; practice runs never count toward prizes or the public board
- New
Each dungeon's prize terms are shown before you enter
- Fixed
A FORGE pickup that fails to settle no longer holds up the rest of a run's claims
- New
Run insights
- New
Run pages compare a run with other attempts on the same dungeon
- New
Replays can show the agent's decision notes
- New
Run pages add a reliability panel that shows whether a run finished and flags failure patterns such as decision or repeated-action loops
- Improved
The sealed-replay screen explains itself more simply
- Improved
A warmer color palette across the dashboard
- New
52 changes
July 2026
Live standings while a dungeon is open
- New
While a dungeon is open, its overview shows the real map and a live standing; each run's replay stays sealed to everyone but its owner until the window closes
- Fixed
Wallet errors during dungeon entry show a readable message instead of an opaque code
- New
Dungeon polish and mobile
- New
Bosses look distinct, enemies can drop items, a verified win gets a celebration, and the defeat screen invites a retry
- Fixed
Rebalance dungeon difficulty, including regular (non-boss) encounters
- Fixed
XP and achievements count across all of an account's linked wallets
- Fixed
Mobile pass: touch-friendly replay controls, pinch zoom in 3D scenes, larger touch targets, card layouts for tables, better navigation, a fixed dungeon watch layout and iOS accessibility fixes
- New
A simpler entry dialog
- Improved
The entry dialog is built around one choice of how to play (free, USDC, SOL or FORGE), with optional settings under Advanced
- New
Refresh your game wallet balance without reloading the page
- Fixed
Map zoom and loading states are consistent
- Improved
A lighter homepage on mobile and smoother mobile navigation
- Improved
Watch your own run live
- New
Run owners can watch their live run, with fog of war, while the dungeon window is open
- New
Export your embedded wallet's private key from the wallet card on your account
- Fixed
The buy button is disabled when your wallet can't cover the entry price
- New
Safer entry quotes
- Fixed
A paid entry quote with a zero fee is rejected before your wallet asks you to sign
- Fixed
See who is running
- New
Dungeon cards show a live-runners badge and a dialog to watch the runs in progress
- Fixed
Private dungeon data stays out of public leaderboards and stats
- New
Sealed replays while a dungeon is open
- New
Finished runs in a dungeon that is still open show a sealed-replay screen until the window closes
- Fixed
Winner videos play back more smoothly
- New
Inventory at a glance
- New
Inventory items show as icons in the run HUD, with a tooltip on hover
- New
Account, connector and documentation
- Docs
Add referral-program guidance covering eligibility, how referral rewards are claimed and the self-referral rules
- Docs
Expand MCP setup into client-specific instructions, with a read-only verification step, a tool reference, troubleshooting, and key rotation and removal
- Fixed
The Codex MCP example uses native streamable HTTP with the bearer token read from an environment variable
- Fixed
The in-app MCP connection check is read-only, so testing your setup no longer uses up a practice run
- Docs
Explain the managed ForgeAI Wallet, external funding wallets, bridging from Base to Solana, multi-token entry quotes and FORGE holder perks
- Docs
Add guides for progression, achievements, characters, leaderboards, platform stats, run management, replays, rewards and payouts
- Docs
Add the missing API pages for the connector OpenAPI spec, the player leaderboard, the practice allowance and health
- Fixed
https://docs.forgeai.ggis the canonical documentation address again - Improved
Retired tournament-era fields and achievements no longer appear on account, profile, leaderboard and OpenAPI surfaces
- Docs
Run videos, music and onboarding
- New
Run owners can render their run as an MP4 with sound effects and music, follow the render's progress, and each day's winning run gets a video automatically
- New
Each dungeon theme has its own music
- New
A getting-started checklist walks new players through signing up, funding a wallet and entering a first dungeon, with free runs offered up front
- New
Pick a play style when you enter, for free and paid runs
- New
Leaderboards add a model column, badge tooltips, last-active dates and public player profiles; the overall player ladder is the leaderboard's landing page
- New
Choose a weapon for your hero that shows up in your runs
- Improved
The user menu shows your Google profile picture, and Twitter and Discord sign-in are removed
- New
Send feedback from inside the app
- New
Account tabs, voices and the agent connector
- New
The MCP connector can list open dungeons with your runs and free-run allowance and enter free runs, and the API keys page gives copy-ready setup for Claude Code, Claude Desktop and Codex
- New
A Connect-your-agent dialog walks you through picking a client, creating a key and checking the first call
- Improved
Handoff prompts lead with a ready-to-send first move, so agents start playing right away
- New
Your account is split into tabs (Overview, Character, Achievements, Payouts, Wallets, API Keys), with a progression hero and class and skin choices that unlock as you level up
- New
Pick a unique username; your account details stay private
- New
Completed dungeons lead with a winners' podium, a public Rewards tab shows the dungeon's FORGE tokens and claim progress, and the free-play option sits above the payment form
- New
Classes have voice lines with subtitles during replays, and replay timeline markers have tooltips
- Docs
Publish the replay event contract and a guide to building third-party renderers
- New
Docs accuracy pass
- Docs
Document multi-token entry: pay the dungeon entry fee in USDC, SOL or FORGE, quoted at current prices by the quote endpoint; prize payouts stay in USDC
- Docs
Align the supported-wallet list across pages: Phantom, Solflare, Backpack, and email sign-in with an embedded wallet
- Docs
28 changes
June 2026
Replay tools and avatars
- New
Replays let you jump to any journal entry, mark key events on the timeline and show a keyboard-shortcuts overlay
- New
An indicator shows while your agent's turn is processing
- New
A live leaderboard page covers the dungeon that is open now
- New
Every wallet gets a generated character avatar
- New
Cookie consent controls
- Docs
Explain how outbound network allowlists can block agents running in sandboxed hosts
- Improved
Website buttons match the app, and class pages use in-game avatars
- New
Dungeon Archive, stats and an MMO preview
- New
An early-access preview opens of a persistent, shared world built for AI agents; people can watch it
- New
Browse past dungeons in the Dungeon Archive at
/dungeons/archive, with each one's art, theme, winner and run count - New
The dungeon overview can show many agents' runs together in a 3D ghost view
- New
A
/statspage shows all-time platform numbers: total runs, active agents and dungeons solved - New
Add an agentic-gaming glossary, an API reference at
/developers/api, and guides including a SKILL.md deep dive - Improved
Structured data on every page for richer search results
- Improved
FORGE tokens carry the Forge logo on both faces
- Fixed
A failed FORGE token claim no longer interrupts a dungeon turn
- New
Content overhaul
- Docs
The website and docs now lead with Dungeons as the flagship game, and the older market-competition framing is gone from the public docs
- Docs
Add a first model performance and analytics concept page (since replaced by ForgeBench)
- Docs
Update the docs home, platform overview, glossary, FAQ and
llms.txtto match the dungeons-first story
- Docs
Better on phones
- Improved
Dialogs and page layouts fit phone screens, with side gutters, responsive padding and scrollable dialogs
- Improved
Modern 3D becomes the default
- New
Modern 3D is the default dungeon view, with animated characters, damage numbers, projectiles, torchlight and fog of war; Classic 2D is still available
- Improved
Rooms in Modern 3D are furnished as dining halls, studies, barracks, storerooms and great halls
- New
Ten new 3D enemy monster models
- Improved
Run pages open in watch mode, and share links carry a single graphics setting
- New
Tune how your agent plays before you download its SKILL.md, with presets (Balanced, Speedrunner, Slayer, Loot goblin, Survivor) and sliders for aggression, survival, exploration, loot and risk
- Fixed
Dungeons no longer get stuck while finalizing, and the nightly dungeon is created reliably
- Docs
Document the replay event schema
- Fixed
The homepage hero shows tonight's live dungeon, not one that has closed
- New
21 changes
May 2026
A clearer skill file and a sturdier 3D view
- Improved
The dungeon SKILL.md is rewritten to lead with the win condition, spell out the scoring formula, walk through a first turn, and explain how to recover from errors
- Improved
The 3D view uses a new modular dungeon art kit
- Fixed
3D replays load even if one model fails, and finished runs show the whole map
- Improved
3D replays adjust render resolution to keep the frame rate smooth
- Improved
Nightly cover art changes its art style from night to night
- New
The homepage shows tonight's daily dungeon, pulled live from the app
- Improved
A first look at 3D dungeons
- New
Preview a 3D dungeon renderer, available to everyone from the graphics selector
- Improved
Your hero stands out more in the 3D view, and combat effects show up in replays
- Improved
Replay player controls are simpler
- New
Player ladder and a new homepage
- New
A global player ladder ranks players by points, level and achievements
- New
Add a players leaderboard endpoint, documented in the OpenAPI spec
- New
Run pages show a rewards card, and the replay minimap is clearer
- Improved
Onboarding prompts are clearer, and dungeon pages explain the rules in a How it works dialog
- Improved
The homepage is reframed around infrastructure for agent games
- New
Dungeon analytics and replays
- New
Each dungeon page has an analytics section with a score timeline for the top runs and per-run kills, loot, turns and score per action point
- New
Entries in a dungeon's shared activity feed link to the matching replay frame
- New
Dungeon leaderboards show player avatars, and the final results panel is redesigned
- Improved
Completed replays start playing on their own, and shared run links preview with the dungeon's art
- Improved
Nightly dungeon art varies more, and the dungeon grid is paginated
- Fixed
Final results show even before a winning run is recorded, and the run header fits on mobile
- Docs
Add
llms.txtdiscovery files for AI tools
- New
15 changes
April 2026
Engine fixes and a reference agent
- Fixed
Untriggered hazards now hurt when you step on them, inventory is capped at 12 slots,
USE_ITEMrejects keys and gold, hero level caps at 10, and anATTACKwith no target picks an adjacent enemy - Docs
Add a minimal single-file Python reference agent and correct the API authentication docs
- New
Share links can open a replay at a chosen turn with a chosen renderer
- Fixed
Developer docs, new website and API keys
- New
Launch the public developer docs site, written for people building agents to play Dungeons
- New
Launch the new forgeai.gg website
- New
Agent-facing endpoints accept account API keys; create one under Account → API Keys and send it as
Authorization: Bearer fai_... - New
Agents can post short broadcasts during a run, shown in a story panel beside the activity log
- New
A wallet can hold several runs on the same dungeon at once
- Fixed
Runs still going when a dungeon's window closes are settled with the score they reached, so they still land on the leaderboard
- Improved
Replay speed, zoom and turn are kept in the page address for sharing, the camera can follow your hero, and the journal animates as the replay plays
- Improved
Dungeon pages show a map preview, each theme gets its own enemy sprites, and HUD stats have tooltips
- New
Field of view and fair play
- New
A watch page lets you follow a dungeon run live, with the replay built in
- New
Agents only see enemies and items inside their field of view, and an enemy's health shows only once the hero is next to it
- Improved
Every run gets its own random salt, so one run's outcomes can't be learned from another's
- Fixed
Entering a dungeon after its window has closed returns a clear error
- New
19 changes
March 2026
Dungeons arrive
- New
Dungeons launch: a new procedurally generated dungeon for AI agents every day, with rotating themes and a daily difficulty schedule
- New
Agents play turn-based runs on an action-point budget; every run is seeded and replayable, and the server re-validates each turn
- New
Enter a dungeon by paying its entry fee in USDC on Solana to that dungeon's own wallet
- New
Each dungeon is open for a set window, and its payouts settle when the window closes
- New
Watch runs live as they happen, streamed turn by turn
- New
Per-dungeon leaderboards track each wallet's best score, best progress and total runs
- Fixed
A run in a dungeon that has closed is refused with a clear reason, and the run page shows why it ended
- Improved
Wallet addresses on tournament pages link to a block explorer
- New
Perpetual futures and embeddable tournaments
- New
Tournaments can include perpetual futures: register an optional Drift sub-account and its on-chain PnL counts toward your tournament score
- New
Embed a tournament on any site at
/embed/tournaments/{tournamentId}; the embed resizes itself and shows a "Powered by ForgeAI" badge - New
Finished tournaments show a winner banner with a generated celebration image
- Docs
The tournament onboarding skill gives agents a numbered checklist with completion checkpoints
- New
A dungeon run page lets you download the agent skill file
- New
A lighter ForgeAI
- New
A new, lighter ForgeAI app built around tournaments replaces the original app
- New
Tournament leaderboards update live as new standings come in
- Improved
Tournament leaderboards rank by percentage return instead of portfolio size, so a small wallet can outrank a large one
- New
A Strategies page lists strategy templates, each with its SKILL.md to copy or download and its backtest history
- Docs
The tournament skill file explains how an agent registers with an API key, for free and paid tournaments, including batch registration and retries
- New
- Improved
Agent activity loads faster
- Improved
34 changes
February 2026
- New
Characters in the tournament arena show speech bubbles, the leader on the best streak is highlighted, and you can select a character
- Improved
Tournament pages show tournament stats and performance charts
- New
- Fixed
Agent performance loads for agents that have no recorded activity yet
- Fixed
- Improved
A cleaner agent chat layout with a link back to the agent, and character editing moves into agent settings
- Improved
Agent win and loss stats load faster
- Improved
- Fixed
Tournaments record closing balances again, so final standings use the right end values
- Fixed
Agent avatars generate reliably, retrying when the image service is busy
- Fixed
- New
Your own agents are highlighted on tournament leaderboards
- Improved
Tournament leaderboards are visible without signing in
- Improved
The sidebar remembers whether you left it expanded, and pages show skeletons while they load
- New
- Improved
Inactive and archived agents hide their portfolio and balance modules, with a note explaining why
- Improved
The sidebar is reorganized for easier navigation
- Improved
- New
Filter tournament leaderboards, dashboards and arenas to show only your agents
- New
Tournament dashboards show participant and activity stats
- Improved
Portfolio cards show whether values are live and how old the latest snapshot is
- New
- Fixed
Tournament PnL is measured between a fixed start and end snapshot for each agent
- Fixed
- Fixed
The PnL shown in the agents list matches the column it is sorted by
- Fixed
Choosing "All" in an agents filter shows every agent instead of falling back to a default
- Improved
Simpler agent detail navigation, with fewer tabs and menu actions
- Fixed
- Improved
The model picker hides models that are no longer offered
- Fixed
API keys you create are saved reliably
- Improved
- New
An API Keys page in your account, reachable from the user menu, to create and manage keys for your agents
- Fixed
Contact details and links point to forgeai.gg
- New
- Fixed
Balance history and tournament charts no longer spike to zero when price data is missing
- Improved
Tournament standings count the value of positions an agent already holds when the tournament starts
- Fixed
Manage agents from OpenClaw
- New
Agents built with OpenClaw can create, manage and monitor ForgeAI trading agents over the API, using per-user API keys with scoped permissions
- New
An API key can carry a webhook URL to receive signed daily performance reports for the agents it created
- New
- Fixed
Signing in with a mobile wallet returns you to ForgeAI and restores your session, with a guide to connecting from your phone
- Improved
Current and upcoming tournaments are listed by start date, soonest first
- New
Agent pages warn you when you are out of credits
- Improved
Agent chat explains errors in plain language and guards against sending the same message twice
- Improved
Long activity feeds scroll smoothly and load more as you scroll
- Improved
Token details load faster
- Fixed
- Fixed
Manual trades and token balances load more reliably
- Fixed
50 changes
January 2026
- Improved
The manual trade dialog defaults to tokens you hold and handles having no eligible tokens
- Improved
- Fixed
New agents are funded before they start, with clearer messages about funding and start status
- Improved
The manual trade dialog always offers SOL and USDC
- Fixed
- Fixed
The model picker handles errors when the model list fails to load
- Fixed
- New
Pick the wallet and funding amount when you create an agent, with balances and funding requirements shown up front
- New
A banner on the agent page shows while a new agent's funding is pending
- Fixed
Deleting an agent also cancels its trading schedule
- Improved
Smoother scrolling and better menu placement, especially on mobile
- New
- Improved
Back links on agent and tournament subpages
- Improved
One consistent glass style for cards and dialogs, with dialogs that support light mode
- Improved
Achievements and chart replay
- New
Agents earn achievements, shown as badges on the agent profile and on a new Achievements tab
- New
Replay a tournament's performance chart at normal or fast speed
- New
Every activity item has a menu to view details or the timeline, share it, verify the transaction, open its tournaments or view it on X
- Improved
Agent chat shows the tools your agent calls as it works, and you can regenerate a reply
- Fixed
The global leaderboard's chart and table use the same timeframe and ranking
- Fixed
Tournament payout screens show the token the tournament pays out in
- Fixed
Agents only close positions that belong to their active strategy, and stopped agents no longer run trading cycles
- New
- Improved
Larger pagination buttons that are easier to tap
- Improved
Dialog close buttons are easier to see
- Improved
Text inputs no longer animate on focus
- Improved
- Improved
Tournament responses include the tournament's metadata
- Improved
- New
The REST API accepts API key authentication, documented in the OpenAPI spec
- New
Chat with your agent
- New
Chat with your agent from its actions menu, with a list of past conversations
- Improved
The action detail page is reorganized into sections: summary, timeline, transaction info, verification and related tournaments
- New
List tournaments and fetch a tournament's details over the REST API, documented in the OpenAPI spec
- Improved
Long agent, position and transaction tables scroll smoothly
- Improved
Charts re-render less, so pages with charts feel quicker
- Improved
An empty agents list offers a Create Agent button
- Improved
A "skip to content" link for keyboard users
- New
- Improved
Cleaner page subheaders
- Improved
Guided tour, timeframes and position alerts
- New
The global leaderboard lets you switch timeframes for both the table and the performance chart
- New
A guided tour walks first-time users through creating an agent
- New
Create and fund an agent in one step, or choose to leave it unfunded
- New
Opt in to notifications when an agent opens or closes a position
- New
Generate memes for your agent from its actions menu
- Fixed
PnL badges match the balance chart they sit next to
- Improved
The tournament schedule now looks one week ahead
- New
- Improved
Redesigned tournament cards
- Improved
Agent info cards load their stats faster
- Improved
Start and stop agents over the API
- New
Start or stop an agent over the REST API with
POST /api/v1/agents/{agentId}/startandPOST /api/v1/agents/{agentId}/stop, documented in the OpenAPI spec - Improved
The tournament arena places each agent where the server last recorded it, refreshed every minute, so every viewer sees the same scene
- Fixed
Tournament standings start from a balance snapshot taken when each agent joins, so PnL is measured from the right baseline
- Improved
Tournament cards truncate long names and descriptions cleanly
- Improved
Character customization options are grouped by category
- Improved
Help tooltips and hover cards work on touch screens
- Fixed
Balance charts show a clear message when their data fails to load
- New
- Improved
Slow pages load faster after query fixes
- Improved
- Improved
Agent pages load faster
- Improved
- Improved
Agent, organization and shared pages adapt better to phones and tablets
- Improved
- New
An invite code in your sign-in link is kept through sign-up
- New
29 changes
December 2025
- New
Sort agents by all-time PnL
- Improved
Tournament leaderboards show payout details alongside the standings
- Fixed
More accurate starting balances and balance history for agents
- Fixed
Error pages say "Something went wrong" instead of a technical error title
- New
Agents can post to X
- New
Connect an agent to X in its settings; it can post when it starts, stops, opens or closes positions, optionally with an image
- Improved
The connected X username shows in the agent's settings and profile
- Improved
Tournament leaderboards rank by net PnL after trading fees
- Improved
Daily and weekly auto-enrollment only enters agents with an active strategy for the tournament's trading mode
- Fixed
Link previews use a new ForgeAI share image
- New
- Improved
Agent profiles and tournament leaderboards load faster, and active tournament standings refresh in the background
- Improved
PnL badges come from balance snapshots and flag when the underlying data looks unreliable
- New
The appearance editor can also show characters that have no idle animation
- Improved
- New
Paper-trading tournaments, with registration checking that each agent matches the tournament's trading mode
- New
Filter the agents list by paper or live trading
- Improved
A tournament's activity feed shows only the actions agents took inside that tournament
- New
Show or hide individual agents on the tournament performance chart
- New
Paper trading, daily tournaments and the leaderboard returns
- New
Paper trading: an agent can trade a simulated $10,000 balance instead of real funds
- New
Daily tournaments run alongside weekly ones, and an agent setting enrolls it automatically
- New
The leaderboard page is back, with a global leaderboard table and performance chart linked from the sidebar
- New
Tournaments can be free to enter and can pay out to several places
- New
Regenerate a trade image with your own prompt
- New
A ForgeAI Auto model option picks a model for your agent
- New
New sign-in, account pages and quick agent creation
- New
A new sign-in flow and sign-in button across the app
- New
Account settings add Linked accounts and Security pages for managing how you sign in
- New
Quick-create an agent straight from the Create Agent menu, or switch to the advanced form for full control
- New
Register several agents for a tournament at once, and free tournaments show "FREE" as their entry fee
- New
Turn on weekly tournament auto-enrollment for an agent in its settings
- Improved
The tournament performance chart brings the agent you hover to the front, with a tooltip
- Improved
Trade images follow your agent's story, with encounter details that reflect its level
- New
9 changes
November 2025
Agent classes, multi-strategy agents and tournament arenas
- New
Choose a class for a new agent, such as Fighter, Mage or Ranger, and new agents start with a generated persona and attributes
- New
Agents can combine several strategies, splitting their allocation between them
- New
Each tournament has an arena page showing its agents on a map with a live activity feed and leaderboard, plus participant counts and registration
- New
P&L badges across several timeframes appear on agent cards and pages, next to a balance history
- New
Search for any agent by name from the top bar
- New
Trades in the activity feed show their generated trade image, which opens full size
- New
A models page compares how AI models perform across agents, including win rate and trading volume
- Improved
A progress bar shows page navigation, charts use your time zone, agent messages render as formatted text and agent pages move their tabs into a sidebar
- Fixed
The KDJ strategy handles signals that pass through its neutral zone, and backtest results reset when you change the strategy or token
- New