🧠
Agent Memory & Project State
Index, query, and verify what your code is — and what your agents did. Repo memory, tasks, handoffs (kuda, myco, atta, mycena)
GaiaPut AI agents to work — on your terms
Open infrastructure for agent-driven development
Open infrastructure for agent-driven development
We build open infrastructure so people and agents can own the AI that works for them.
We're building the missing layers between coding agents and the repositories they work on — memory (kuda), coordination (sturn), verification (mimus), CI (bupha), sessions (sepia), orchestration (peregrin), project management (myco), and calendars (cicada). Open, minimal, composable — a stack agents can actually run on.
The principles behind how we build.
Every interface is a CLI, protocol, or data format built to be driven, not clicked.
The suite manages its own development — dogfooding is the test suite.
Small single-purpose tools, every concern behind a port, any layer swappable.
MCP, ACP, ndjson JSON-RPC — plug in, no glue code.
Tasks, calendars, claims, pipelines: declarative, versioned, reproducible.
Open source, self-hosted — your AI works for you, not the other way around.
Discover our diverse range of projects focused on developing minimal and viable solutions using cutting-edge technologies.
A hippocampus for your codebase — repo memory: index, query, verify
The murmuration layer for your repo — evented coordination: ops, claims, topics
Spots the cuckoo eggs in your repo — claim verification: docs-as-tests, memory audit
The oxpecker on your repo's back — headless CI toolkit: watch, queue, run, report
The bug that shows up on time — calendars as code: declare, plan, apply, drift
The technologies we reach for, by layer.
We are always looking for passionate individuals to join us. If you're interested in collaborating or contributing to our projects, feel free to reach out!
For inquiries, please contact Luis at [email protected].