Manifold

Manifold is an experimental platform for long-horizon workflow automation with teams of AI assistants.

It supports OpenAI, Google, and Anthropic models, along with OpenAI-compatible APIs for self-hosted open-weight models served through llama.cpp or vLLM.

[!WARNING] 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.

What Manifold does

Manifold 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.

Features

Agent chat

Use a traditional chat interface to assign objectives to specialists. Agent specialists can be configured to render visualizations in addition to text responses.

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.

Image generation

Manifold supports image generation with OpenAI and Google models, as well as local image generation through a custom ComfyUI MCP client.

Example ComfyUI-generated image using a custom workflow.

Observability (work in progress)

Pulse - Scheduled Tasks

Schedule 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.

Workflow editor

Design 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.

Specialist registry

Define and configure AI agents, then build your own team of experts.

Projects

Configure projects as agent workspaces.

Each project is isolated to its own root path. Agents load project skills from that project's skills/ folder, and can also discover universal read-only skills from $HOME/.manifold/skills and $HOME/.agents/skills through dedicated skill tools.

Integrated tools and MCP support

Manifold 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.

Prompts, datasets, and experiments playground

Create, iterate on, and version prompts that can be assigned to agents. Configure datasets and run experiments to understand how prompt changes affect agent behavior.

Deploy a fresh clone

The recommended first-run path is Docker-based and does not require a local Go, Node, or pnpm toolchain.

Prerequisites

For a basic local deployment, you need:

• Docker with Docker Compose support
• An LLM API key or a reachable OpenAI-compatible endpoint
• A writable host directory to use as WORKDIR

Optional local tooling is only needed if you are developing Manifold itself:

• Node 22 and pnpm for running the frontend outside Docker
• Go 1.26.3 for local binary builds
• Chrome or another Chromium-compatible browser if you plan to use browser-driven tools from a host build

Fast path

cp example.env .env
cp config.yaml.example config.yaml

# Edit .env and set at minimum:
#   OPENAI_API_KEY=...
#   WORKDIR=/absolute/path/to/your/manifold-workdir

docker compose up -d pg-manifold manifold

Then open http://localhost:32180.

Self-contained host run

Manifold can also run without external database or telemetry services when you build the manifold binary locally. Enable the embedded Postgres runtime and keep ClickHouse/OTLP unset:

databases:
  embedded: true
  defaultDSN: ""

obs:
  otlp: ""
  local:
    enabled: true
  clickhouse:
    dsn: ""

With that configuration, manifold 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.

For the full deployment walkthrough, see:

• QUICKSTART.md
• docs/deployment.md
• docs/matrix-gateway.md

Developers

Frontend feature gates

make build-manifold builds dist/manifold with the embedded frontend using the stable UI feature gate. Stable builds do render frontend undocumented features still in active development.

To build the same backend and embedded frontend with beta UI links enabled, use either command:

make build-manifold-beta
make build-manifold FEATURE_GATE=beta

The build passes FEATURE_GATE through to Vite as VITE_MANIFOLD_FEATURE_GATE.

Forge harness

Manifold includes an optional Forge-style guarded agent loop for workflow enforcement, tool-error recovery, and control-flow-safe compaction. It is disabled by default. See docs/forge_harness.md for modes, configuration, rollout guidance, and deterministic scenario tests.