Memory and state

Persistent memory layers that give agents recall across turns and sessions: knowledge graphs, vector stores, and session-capture tools that survive a restart. The state a harness needs but rarely ships with.

#	Project	Stars	Tier	OSS	Description
1	claude-mem memory	109k	slightly complex	✅	Session-memory plugin for Claude Code, Codex, OpenClaw, Gemini, Copilot, and more: captures everything an agent does during a session, AI-compresses it, and injects the relevant context into future sessions. Session-to-session memory as a drop-in.
2	Mem0 memorypython	68.2k	slightly complex	✅	Universal memory layer for AI agents: stores user/org/session memory, retrieves on demand. Apache-2.0; the de-facto memory primitive paired with most harnesses in 2026.
3	cognee memoryragworkflowpython	33k	slightly complex	✅	Open-source memory layer for agents: an extract–cognify–load pipeline that turns your data into a queryable knowledge graph plus vector store, so agents recall facts and relationships across sessions instead of re-reading context.
4	Graphiti (Zep) memoryragworkflowpython	32.4k	slightly complex	✅	Zep's open-source memory engine: real-time temporal knowledge graphs that track how facts about users and entities change over time, so agents can answer "what was true when." The layer behind Zep's hosted memory platform.
5	beads memory	28.4k	mostly simple	❓	Portable persistent-memory layer for coding agents: tracks decisions and task state outside the harness's own context window so it survives session resets and model swaps.
6	deja mcpide	1.3k	mostly simple	✅	Memory layer built from the session transcripts that Claude Code, Codex, Cursor, and 39 other agents already write to disk, so recall starts with history from before it was installed. It wires recall into each harness the way that harness supports: hooks at session start, before an edit or command, and after a command fails, plus an MCP tool; local BM25 search in one Go binary, with credentials redacted as the index is built.