agent-memory vs cq
Persistent memory for coding agents compared
agent-memory and cq help coding agents reuse knowledge across sessions. agent-memory organizes session notes into tiered memory and generates AGENTS.md context, while cq provides a structured store for agents to query and contribute lessons, locally or through shared services.
agent-memory: Give Coding Agents Persistent, Tiered Memory
agent-memory turns coding-session notes into organized, tiered knowledge and generates an AGENTS.md section with relevant context for new threads. It is a TypeScript tool for teams and developers who want agents to reuse knowledge without relying on manual searches.
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.
| agent-memory | cq | |
|---|---|---|
| Language | TypeScript | Go |
| License | — | Apache-2.0 |
| Stars | 7 | 1.3k |
| Forks | 0 | 69 |
| Last analyzed | Oct 4, 2026 | Oct 3, 2026 |
Key differences
- agent-memory consolidates session notes into hot, warm, and cold memory; cq focuses on querying, proposing, confirming, and reviewing structured lessons.
- agent-memory generates AGENTS.md content for new threads; cq guides agents to check existing knowledge before acting and after errors.
- agent-memory is written in TypeScript and stores memory in files; cq is written in Go and supports local SQLite storage as well as hosted and self-hosted services.
- agent-memory documents Amp and generic shell adapters; cq lists installation targets for Claude, Codex, Copilot, Cursor, Devin Desktop, OpenCode, and Pi, plus MCP tools and SDKs.
- cq is in 0.x and warns of expected breaking changes; agent-memory's supplied facts do not describe a version or maturity status.
- cq is Apache-2.0 licensed and has 1.3k stars and 69 forks; agent-memory has 7 stars and no forks in the supplied facts.
Choose agent-memory if you…
- want to turn session notes into tiered, reusable memory and generated AGENTS.md context.
- prefer file-based memory and a standalone CLI with adapter-based integrations.
- need to reorganize accumulated notes using LLM-assisted consolidation and defragmentation.
Choose cq if you…
- need agents to query, contribute, and validate structured lessons.
- want local SQLite storage or a shared hosted or self-hosted knowledge service.
- use one of cq's listed agent integrations or want its MCP tools, CLI, or Go and Python SDKs.
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.