ai-memory vs cq
Shared coding-agent knowledge compared
ai-memory and cq help coding agents carry useful context across sessions, machines, and teams. ai-memory captures activity as a git-backed Markdown wiki with handoffs, while cq manages structured, reusable lessons that agents can query and submit for review.
ai-memory: Share Long-Term Memory Across Coding Agents
A self-hosted Rust service that captures coding-agent activity into a searchable, git-backed Markdown wiki and hands work between agents. It suits developers and teams who want portable project memory without requiring LLM calls.
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.
| ai-memory | cq | |
|---|---|---|
| Language | Rust | Go |
| License | MIT | Apache-2.0 |
| Stars | 9.1k | 1.3k |
| Forks | 632 | 69 |
| Last analyzed | Oct 10, 2026 | Oct 3, 2026 |
Key differences
- ai-memory records prompts, tool calls, and session boundaries; cq focuses on reusable lessons that agents query, propose, confirm, or flag.
- ai-memory stores its source of truth in Markdown files; cq supports a local SQLite store and remote services.
- ai-memory is written in Rust under the MIT license; cq is written in Go under the Apache-2.0 license.
- ai-memory's basic capture, search, and handoffs work without LLM API calls; cq guides agents to search before acting and can optionally reflect on sessions to identify lessons.
- ai-memory is self-hosted; cq offers local storage, Mozilla.ai's hosted service, and self-hosting.
- cq is a 0.x project and warns that breaking changes are expected; ai-memory's listed project facts do not include a comparable maturity warning.
Choose ai-memory if you…
- want project context stored as inspectable, editable, git-backed Markdown.
- need activity capture and handoffs between agents without requiring LLM API calls for the basic workflow.
- need shared project memory across machines or teammates, with personal handoffs and user attribution.
Choose cq if you…
- want agents to query and contribute structured, reusable lessons.
- need a choice of local SQLite storage, a hosted service, or a self-hosted server.
- want integrations and published tools including a CLI, Go and Python SDKs, and a schema.
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.