{"id":25216520,"url":"https://github.com/intelligencedev/manifold","last_synced_at":"2026-05-14T04:02:35.982Z","repository":{"id":276236718,"uuid":"927421008","full_name":"intelligencedev/manifold","owner":"intelligencedev","description":"Manifold is an experimental platform for enabling long horizon workflow automation using teams of AI assistants.","archived":false,"fork":false,"pushed_at":"2026-03-02T02:50:27.000Z","size":105398,"stargazers_count":482,"open_issues_count":4,"forks_count":29,"subscribers_count":11,"default_branch":"master","last_synced_at":"2026-03-02T06:40:34.426Z","etag":null,"topics":["agents","artificial-intelligence","automation","go","llm","retrieval-augmented-generation","visual-coding","vuejs"],"latest_commit_sha":null,"homepage":"https://intelligence.dev","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/intelligencedev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-02-04T23:28:34.000Z","updated_at":"2026-02-25T14:33:01.000Z","dependencies_parsed_at":"2025-02-22T07:26:28.029Z","dependency_job_id":"b4aef56e-1476-4d80-a412-142dba3e3ef4","html_url":"https://github.com/intelligencedev/manifold","commit_stats":null,"previous_names":["intelligencedev/manifold"],"tags_count":52,"template":false,"template_full_name":null,"purl":"pkg:github/intelligencedev/manifold","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligencedev%2Fmanifold","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligencedev%2Fmanifold/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligencedev%2Fmanifold/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligencedev%2Fmanifold/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/intelligencedev","download_url":"https://codeload.github.com/intelligencedev/manifold/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intelligencedev%2Fmanifold/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30032373,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-03T03:27:35.548Z","status":"ssl_error","status_checked_at":"2026-03-03T03:27:09.213Z","response_time":61,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","artificial-intelligence","automation","go","llm","retrieval-augmented-generation","visual-coding","vuejs"],"created_at":"2025-02-10T19:18:26.750Z","updated_at":"2026-05-14T04:02:35.964Z","avatar_url":"https://github.com/intelligencedev.png","language":"Go","funding_links":[],"categories":["artificial-intelligence","vuejs","Vue"],"sub_categories":[],"readme":"# Manifold\n\nManifold is an **experimental** platform for long-horizon workflow automation with teams of AI assistants.\n\nIt supports OpenAI, Google, and Anthropic models, along with OpenAI-compatible APIs for self-hosted open-weight models served through [llama.cpp](https://github.com/ggml-org/llama.cpp) or [vLLM](https://github.com/vllm-project/vllm).\n\n\u003e [!WARNING]\n\u003e Manifold is an experimental frontier AI platform. Do not deploy it in production environments that require strong stability guarantees unless this README explicitly states otherwise.\n\n## What Manifold does\n\nManifold is built for workflows that go beyond one-shot prompts. It gives you a workspace where specialists, tools, projects, and workflows can work together on multi-step objectives over extended periods.\n\n## Features\n\n### Agent chat\n\nUse a traditional chat interface to assign objectives to specialists. Agent specialists can be configured to render visualizations in addition to text responses.\n\n![chat](docs/img/chat.webp)\n\n_Specialists can collaborate across multiple turns. Manifold is designed to take advantage of the long-horizon capabilities of frontier models and can work on complex objectives for hours._\n\n### Image generation\n\nManifold supports image generation with OpenAI and Google models, as well as local image generation through a custom ComfyUI MCP client.\n\n![image generation](docs/img/imggen.webp)\n\n_Example ComfyUI-generated image using a custom workflow._\n\n### Observability (work in progress)\n\n![chat](docs/img/overview.webp)\n\n### Pulse - Scheduled Tasks\n\nSchedule tasks for agent specialists to execute in time intervals, daily, or only once at a defined date and time. Send results to various external services. Matrix is natively supported, but Skills or MCP's can extend the channels Manifold has access to.\n\n![pulse](docs/img/pulse.webp)\n\n### Workflow editor\n\nDesign agent workflows with a visual flow editor. __MCP tools are exposed as nodes automagically. Saved workflows become tools that can be invoked by specialists or inserted as nodes into other workflows.__ It's workflows all the way down.\n\n![workflow editor](docs/img/flow.webp)\n\n![workflow editor 2](docs/img/flow2.webp)\n\n### Specialist registry\n\nDefine and configure AI agents, then build your own team of experts.\n\n![specialists](docs/img/specialists.webp)\n\n### Projects\n\nConfigure projects as agent workspaces.\n\nEach project is isolated to its own root path. Agents only load skills from that project's `.skills/` folder, so every project that needs reusable skills must define its own `.skills` directory inside the project root.\n\n![projects](docs/img/projects.webp)\n\n### Integrated tools and MCP support\n\nManifold includes built-in tools for agent workflows and supports MCP to extend agent capabilities. You can configure multiple MCP servers and enable tools individually to manage context size more precisely.\n\n![mcp](docs/img/mcp.webp)\n\n### Prompts, datasets, and experiments playground\n\nCreate, iterate on, and version prompts that can be assigned to agents. Configure datasets and run experiments to understand how prompt changes affect agent behavior.\n\n![playground](docs/img/playground.webp)\n\n## Deploy a fresh clone\n\nThe recommended first-run path is Docker-based and does **not** require a local Go, Node, or `pnpm` toolchain.\n\n### Prerequisites\n\nFor a basic local deployment, you need:\n\n- Docker with Docker Compose support\n- An LLM API key or a reachable OpenAI-compatible endpoint\n- A writable host directory to use as `WORKDIR`\n\nOptional local tooling is only needed if you are developing Manifold itself:\n\n- Node 22 and `pnpm` for running the frontend outside Docker\n- Go 1.25 for local binary builds\n- Chrome or another Chromium-compatible browser if you plan to use browser-driven tools from a host build\n\n### Fast path\n\n```bash\ncp example.env .env\ncp config.yaml.example config.yaml\n\n# Edit .env and set at minimum:\n#   OPENAI_API_KEY=...\n#   WORKDIR=/absolute/path/to/your/manifold-workdir\n\ndocker compose up -d pg-manifold manifold\n```\n\nThen open \u003chttp://localhost:32180\u003e.\n\n### Self-contained host run\n\nManifold can also run without external database or telemetry services when you build `agentd` locally. Enable the embedded Postgres runtime and keep ClickHouse/OTLP unset:\n\n```yaml\ndatabases:\n  embedded: true\n  defaultDSN: \"\"\n\nobs:\n  otlp: \"\"\n  local:\n    enabled: true\n  clickhouse:\n    dsn: \"\"\n```\n\nWith that configuration, `agentd` starts a bundled PostgreSQL process for durable state and serves metrics, logs, and traces from bounded process-local telemetry. You still need an LLM provider, which can be a remote API key or a local OpenAI-compatible endpoint.\n\nFor the full deployment walkthrough, see:\n\n- [QUICKSTART.md](./QUICKSTART.md)\n- [docs/deployment.md](./docs/deployment.md)\n- [docs/matrix-gateway.md](./docs/matrix-gateway.md)\n\n## Developers\n\n### Frontend feature gates\n\n`make build-manifold` builds `agentd` with the embedded frontend using the stable UI feature gate. Stable builds do render frontend undocumented features still in active development.\n\nTo build the same backend and embedded frontend with beta UI links enabled, use either command:\n\n```bash\nmake build-manifold-beta\nmake build-manifold FEATURE_GATE=beta\n```\n\nThe build passes `FEATURE_GATE` through to Vite as `VITE_MANIFOLD_FEATURE_GATE`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintelligencedev%2Fmanifold","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintelligencedev%2Fmanifold","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintelligencedev%2Fmanifold/lists"}