(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.
Persistent local memory for Claude Code. Every tool call, every file edit, every thinking block from every session — stored verbatim on your machine. Semantic recall in 126ms with zero API calls.
Persistent, user-owned memory for AI agents over hosted MCP. Remember decisions, recall project context, manage TODOs, and govern memory lifecycle across sessions.
Recorded decisions from git history, delivered to the agent before it edits. Constraints, alternatives already ruled out, and warnings left by whoever was here last.
Memory for coding agents: hybrid search/recall, entity resolution, and a gated git-first write over a self-hosted, OAuth2-authenticated tailnet MCP. The default memory layer for coding agents.
Quietly captures your Claude Code sessions and distills how your thinking, habits, and knowledge change over time — a dated growth archive with provenance, served over MCP. Also ingests any text corpus (notes, articles, market news) to track how THAT changed instead. Local, single Go binary.
Persistent agent memory across sessions. Corrections stick, context compounds, every session starts smarter. Cross-session knowledge base built on Zettelkasten.
Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.
6
changed yesterdayA
tokens not measured
originalMIT
Persistent memory for AI assistants — runs locally on your machine. Remember every decision, debugging session, and architecture debate across sessions. One MCP server, zero cloud dependencies, works on a Raspberry Pi.
Milestone-triggered, in-session work diary for Claude Code. The model records meaningful milestones to plain-markdown log + status files as it works, across all projects. No database.