Fidelis Memory MCP server

Fidelis Memory

<!-- mcp-name: io.github.hermes-labs-ai/fidelis-memory -->

Local-first, zero-LLM memory for Codex, Claude Code, and AI agents.

83.2% R@1 in a checked-in 470-question LongMemEval-S retrieval run. A separate checked-in run answered 317 of 434 graded questions correctly (73.0%, Wilson 95% CI [68.7%, 77.0%]) with an LLM reading Fidelis retrieval. The default retrieval path itself makes no LLM call.

Stop re-explaining context to your agent. fidelis returns your original notes verbatim through a local-first service. Your agent already calls an LLM to think; it should not need another one just to remember. Designed for developers. The default zero-LLM retrieval path does not send memory content to an LLM. The documented fidelis init service configuration also disables mem0 and Chroma telemetry. That can reduce third-party data exposure, but deployments still own their security and compliance assessment.

your notes / sessions
       ↓
local memory store      (~/.cogito/, fully local)
       ↓
fidelis retrieval       (BM25 + dense + RRF, no LLM)
       ↓
original passages       (verbatim, never rephrased)
       ↓
Codex / Claude Code / your agent

What fidelis is:

• model-API independent by default - the default retrieval path makes no model API call; local compute and storage still have costs
• private - local memory store by default
• faithful - original stored passages returned, not paraphrases
• measured - checked-in LongMemEval-S retrieval and QA artifacts are linked below
• installable - documented MCP paths for Codex, Claude Code, GitHub Copilot CLI, Gemini CLI, and OpenClaw

Fidelis is deliberately narrower than a hosted memory platform. Check the user-fit matrix before installing: it names the workflows 0.2.0 supports, the prerequisites it assumes, and the cases it does not yet serve.

Registries

io.github.hermes-labs-ai/fidelis-memory, currently registered at version 0.1.0. The 0.2.0 manifest is included in this release and must be published separately after its package release.

• Official MCP Registry —

independent third-party server listing.

• Glama MCP server directory —

Docker / Glama

docker build . runs the MCP stdio server (fidelis mcp serve) by default — what a registry build/inspector (e.g. Glama) talks initialize / tools/list to — and needs no Ollama or running fidelis-server. To run the HTTP memory server in a container instead, set FIDELIS_ENTRYPOINT=http (see docker-compose.yml for the full stack including Ollama).

Quickstart

Platform support: macOS or Linux (Windows not yet supported). Install Ollama via

Homebrew on macOS, or the Ollama Linux install

on Linux. See Requirements for the full prerequisite list.

# 0. one-time: Ollama + the local embedder (~280 MB)
brew install ollama && ollama serve &
ollama pull nomic-embed-text

Shortened. The full README is on GitHub.