Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
Agent platform build prompts
Each file in this directory is a complete, self-contained build brief for one missing surface of the three.ws agent platform. Hand a file to an agent as its task. Every brief assumes the agent has read CLAUDE.md and this page.
Order
Dependencies flow downward. Rows in the same tier can run in parallel.
| Tier | Prompt | Why this order |
|---|---|---|
| 1 | 01 CLI setup and login | Everything else gets installed through it. |
| 1 | 03 MCP tool policy and the model-facing skill | Every later tool registers under it. |
| 1 | 05 Agents REST parity | The SDK, gateways and loop all wrap these routes. |
| 1 | 17 One MCP endpoint, one OAuth | Every later tool mounts here. |
| 1 | 18 Open-model roster and free-tier models | Needed by the free tier and the local runtime. |
| 1 | 29 Free tier, pricing and rate limits | Every metered brief prices against data/plans.json. |
| 2 | 04 Community skills registry | Installs through the CLI. |
| 2 | 06 Agents SDK | Wraps tier 1 routes. |
| 2 | 15 Gasless launch and the launch command | Adds a CLI subcommand. |
| 2 | 16 Self-funded inference | Wallet plus credits. |
| 2 | 19 Self-custody, signers, key export, balance history | Changes the signing contract every financial brief uses. |
| 2 | 30 Trading tool parity | Exposes existing trading as tools; venue interface for later legs. |
| 2 | 33 Account, X posting policy, Google linking | Account objects the gateways and status tools read. |
| 3 | 07 Perps, 08 Lending, 09 Prediction markets | New execution venues under the policy. |
| 3 | 10 Whole-agent marketplace with bids | Transfers custody; depends on 19. |
| 3 | 11 Agent mail, 12 Agent cards, 31 Human tasks | Real-world surfaces; provider adapters plus tools. |
| 3 | 21 Memory and self-improvement | Needs runs (05) and prompt-only skills (04). |
| 3 | 22 External MCP integrations for agents | Needs the policy (03) and the unified endpoint (17). |
| 3 | 25 Sandboxed code execution, 26 Tool gateway | New default tools under the policy, metered by 29. |
| 3 | 28 Public economics | Reads the fee settings the launch brief unifies. |
| 4 | 13 Telegram and Discord, 24 Slack, WhatsApp, Signal, SMS, email, voice | Uses runs, link codes and mail. |
| 4 | 20 Local agent runtime and TUI | Uses 17, 25, 26, 21 and the gateway. |
| 4 | 35 Always-on strategy loop | Uses runs, memory, budgets and guards. |
| 4 | 27 Bounties and hackathons | Creates runs from bounties; feeds 28. |
| 4 | 32 EVM secondary leg | Extends the venue interfaces after Solana is complete. |
| 5 | 14 Desktop app release | Ships the console over everything above. |
| 5 | 23 Distribution into every agent framework | Packages 01, 03 and 17 for other agents. |
| 5 | 34 Localization | Translates what exists. |
| 5 | 36 Agent evals and replay | Measures everything above; smoke suite into the gate. |
Rules that apply to every brief
CLAUDE.mdgoverns. The four stop-and-ask gates apply, and nothing else stops the work. In particular: any fund-moving action in a test or dry run renders recipient, amount, token and chain and waits for the owner's explicit yes.- Solana first. Every surface ships and is verified on Solana before any EVM leg is considered.
- No mocks, no placeholders, no TODOs, no sample arrays. Every tool, route, page and state is real and wired.
- Every fund-moving or irreversible tool takes an explicit confirm flag, is disabled by default, and has a quote or preview tool that must be called first. Prompt 03 defines the shared policy; every later prompt registers its tools under it.
- Each brief ends only when the definition of done in
CLAUDE.mdholds: reachable in the UI, exercised in a real browser, no console errors, tests green withnpm test, docs written,data/changelog.jsonentry appended,STRUCTURE.mdrow added for a new surface,npm run audit:docsclean,npm run check:rules -- --paths <your files>clean. - Never name a third-party token in committed code, fixtures or docs. Refer to venues by capability and by the module that integrates them. The promoted coin is
$THREEonly. - Commit your own finished work promptly with explicit paths and a message that describes the diff.