Connect to models with Freeport. Carry context with Engram. Test agent tools with MCP-Jest. Three independent projects, each with a clear purpose and source you can inspect.
One gateway. Your infrastructure.
An open-source LLM gateway for routing requests, managing budgets, and understanding what your models are doing. Run it in your own environment.
npx @reallyartificial/freeportYour gateway. Your keys. Your choice of provider.
Context worth carrying forward.
An agent memory system that retains facts, retrieves relevant context, and reflects on what it has learned. Use it as a TypeScript library or an MCP server.
Confidence in the tools agents call.
Automated testing for MCP servers. Check tools, resources, and prompts with repeatable tests, snapshots, and results you can use in CI.
Each project stands on its own. The shared standard is openness, control, and evidence.
Our principlesWe think about the whole life of an agent: what it connects to, what it remembers, how it acts, and how its work earns your trust.
How should agents reach the models they need?
FreeportWhat should an agent carry forward?
EngramHow can an agent work within clear boundaries?
Area of inquiryWhat would count as evidence that it worked?
MCP-JestWhat makes a system dependable over time?
Area of inquiryIndependent projects sharing a field of work. Unlinked areas remain open questions.
Our journal records what we build, the tradeoffs we make, and the questions we have yet to answer.
Read the journal