cq vs agentmemory
Shared knowledge and persistent memory for coding agents
cq and agentmemory both help coding agents reuse context across sessions and tools. cq focuses on structured, reviewed lessons that agents can query and contribute, while agentmemory captures session activity and makes searchable project memory available through MCP and REST.
cq: Share Collective Learning Between AI Agents
cq is a knowledge store and workflow for coding agents to query, contribute, and validate reusable lessons. It helps teams and individual developers avoid repeating debugging work across agent sessions and machines.
agentmemory: Persistent Memory for AI Coding Agents
agentmemory gives coding agents persistent, searchable memory across sessions and tools. It captures work through agent integrations and exposes shared memory through MCP and REST, with a local-first runtime built on iii-engine.
| cq | agentmemory | |
|---|---|---|
| Language | Go | TypeScript |
| License | Apache-2.0 | Apache-2.0 |
| Stars | 1.3k | 29.1k |
| Forks | 69 | 2.5k |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- cq stores structured lessons that agents can propose and humans review; agentmemory captures prompts and tool activity through lifecycle hooks and organizes observations into memory tiers.
- cq supports local SQLite, a hosted service, or a self-hosted server; agentmemory provides a local-first runtime built on iii-engine and exposes memory through MCP and REST.
- cq is written in Go and provides Go and Python SDKs; agentmemory is written in TypeScript.
- cq is in 0.x and warns that breaking changes are expected; agentmemory's supplied considerations call out its engine dependency and open issues.
- cq offers tools for querying, proposing, confirming, and flagging knowledge; agentmemory adds BM25 search, optional vector and graph matching, a viewer, and session replay.
Choose cq if you…
- need reviewed, reusable lessons rather than automatic capture of session activity.
- want local SQLite storage or a hosted or self-hosted shared knowledge store.
- prefer a workflow with explicit tools for proposing and validating knowledge.
Choose agentmemory if you…
- want automatic capture of prompts and tool activity through agent hooks.
- need searchable project memory across sessions, with MCP or REST access.
- want memory search options such as BM25, optional embeddings, and graph-based matching.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.