devrecall

- Local-first.SQLite on your laptop. Tokens in~/.devrecall/tokens/(0600). The Cloudflare Worker relay is a pass-through for OAuth callbacks only — it never sees your data.
- LLM-optional.Bundled embeddings run offline (ONNX +all-MiniLM-L6-v2). Use local Ollama for chat, or bring your own OpenAI/Anthropic key.
- Open source.MIT-licensed. Audit it, fork it, build it from source.

brew install --cask pavelpilyak/devrecall/devrecall

InstallsDevRecall.appand puts thedevrecallCLI on yourPATH.

git clone https://github.com/pavelpilyak/devrecall.git cd devrecall make build # → bin/devrecall

Requires Go 1.22+ with CGO enabled (for SQLite FTS5).

Then connect a source and generate your first standup:

devrecall auth github # or: slack, google, jira, linear, gitlab, bitbucket devrecall standup

make build # bin/devrecall make test # tests with race detector make lint # golangci-lint

Build tags:fts5enables SQLite full-text search;GOenables hugot's pure Go ONNX backend for embeddings.

Local code-knowledge graph + bi-temporal mistakes memory for AI coding agents. Serves a ranked structural packet instead of whole files on read/grep, and surfaces fixes your repo already reverted (mined from git history). Zero cloud, Apache-2.0.

projectmem is a local-first memory layer for AI coding agents (MCP server) — it captures issues, attempts, fixes, and decisions, then warns at git commit before you repeat a mistake. Python, runs locally, works with Claude, Cursor, Antigravity, and Codex

Self-hosted MCP server + dashboard that gives agents shared memory over a git-backed folder of markdown.

Rust MCP server that gives AI coding agents architectural awareness — persistent knowledge graph, blast radius analysis, co-change detection via git, and local semantic search. No API keys, runs entirely on-premise.

A MCP server that connects with LangChain Checkpointers, Memory Stores to aid in monitoring and observability during development of AI Applications

Local-first, state-centric memory for coding agents — remembers your project's conventions and how you like to work. 100% local, over MCP

OpenMemBrain is the intelligent membrane for AI coding memory. It autonomously reads and learns from your coding sessions — you never have to tell it what to save. It selectively absorbs project knowledge, blocks secrets, filters noise, resolves conflicts, and persists only what matters.

Persistent AI memory across tools — remember your preferences, code standards, and decisions across Claude Code, Cursor, Codex, and any MCP tool. Local-first, zero-cloud.

Provides local repo-intelligence by indexing source, symbols, call graphs, Git/GitHub history, and source-bound repo memories into a local database for coding agents.