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