A small lab in the open

Open-source AI with depth.

Local-first, security-first, modular AI tooling — composable parts for people who want to look beneath the surface.

~/fathom

# Install and chat in under a minute
$ brew install darklake-ai/fathom/fathom
$ fathom init --global
$ fathom

# or via curl
$ curl -fsSL https://fathom.darklake.ai/install.sh | sh

  agent      claude-opus-4 (7 tools + persona)
  workspace  /Users/you/fathom-data
  commands   /quit  /help

› summarize the prs i was tagged in this week

How we build

A short list of things we won't compromise on.

Local-first by default

Your data, your machine. Nothing leaves the device unless you explicitly opt in. Even our cloud features (when we add them) will be optional, not the default.

Security as scaffolding

Hash-chained audit log, encrypted credential vault, egress proxy, sandboxed skills. Not features — load-bearing structure. If it's not auditable, we don't ship it.

One binary, no Kubernetes

Most agent platforms ship a control plane. We ship a single static binary. If you can run `curl | sh`, you can run our stack.

Multi-LLM, no lock-in

Claude, OpenAI, Ollama — your choice per session. The agent loop is provider-agnostic. Switch in one line. Bring your own keys.

Composable, not monolithic

Every piece — Fathom, Chasm, Charon, Beacon, Dream, Sigil — is a standalone binary with a wire-protocol API. Use one. Use all. Swap any of them for someone else's. Standard formats (OTLP, OAuth, OIDC) so nothing's a dead end.

Built in the open

Permissive licenses, every commit public, no closed-source core. We'd rather ship a smaller thing that you can fork than a bigger thing you can't see. Issues and PRs are how we ship the roadmap.