palinode

Persistent long-term memory for AI agents — with provenance.

*A palinode is a poem that retracts what was said before and says it better. That's what memory compaction does.*

Git-native. Markdown-first. No database required.

---

AI agents wake up with amnesia every session. They don't remember who you are, what you're working on, or what was decided yesterday. You waste turns re-explaining context that should already be there. Current solutions either don't scale (flat files), produce uncurated noise (vector-only stores), or lock you into opaque databases you can't inspect.

Palinode is persistent memory for LLM agents that stores everything as typed markdown files — human-readable, git-versioned, greppable. A hybrid search index (SQLite-vec + BM25) makes memories searchable by meaning *and* keyword. An MCP server exposes 14 tools so Claude Code, Cursor, Codex, Antigravity, OpenClaw, or any MCP client can search, save, and manage memories. A session skill auto-captures milestones and decisions during coding.

Works with any LLM backend. Tested with OLMo, Qwen, and Claude. If every service crashes, cat still works.

| Turn | What happens | Tokens | |---|---|---| | Turn 1 | Core memory injected (people, projects, decisions) | ~4,200 | | Every turn after | Relevant search snippets for your message | ~300 | | Trivial messages ("ok", "yes", "👍") | Nothing — skipped automatically | 0 |

~300 tokens per turn. Less than a sentence of output. The alternative — re-explaining your project every session — costs the same tokens with none of the benefit.

---

Most agent memory systems are opaque databases you can't inspect, flat files that don't scale, or graph stores that require infrastructure. Palinode is memory with provenance — the only system where you can git blame every fact your agent knows.

• **Git