Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Most AI agent developers today who run multiple agents (Claude Code + Codex + Cursor + Copilot) have been paying the debugging cost repeatedly across agents -- agent A hits an undocumented API bug, fixes it, forgets it; agent B hits the same undocumented API bug a week later, re-debugges from scratch. mozilla-ai/cq inverts that pattern: an Apache-2.0 Mozilla.ai open standard for shared agent learn
Who should use it
Who should skip it
Move on from cq: Apache-2.0 Mozilla.ai Open Standard for Shared Agent Learning (Query / Propose / Confirm / Flag / Status) if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
cq: Apache-2.0 Mozilla.ai Open Standard for Shared Agent Learning (Query / Propose / Confirm / Flag / Status) is tracked by RepoRadar as a tool in the Radar section. It was first seen on 2026-07-08 and last updated on 2026-07-08. The current verdict is 'try now' with a Silver tier and easy setup difficulty. Across RepoRadar's eight signals, cq: Apache-2.0 Mozilla.ai Open Standard for Shared Agent Learning (Query / Propose / Confirm / Flag / Status) is strongest on novelty (9.0) and workflow potential (8.9) and weakest on maturity (5.7) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned cq: Apache-2.0 Mozilla.ai Open Standard for Shared Agent Learning (Query / Propose / Confirm / Flag / Status) a composite score of 7.8 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 0.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The 1217* / 62-fork / 2-subscriber repo is at active maintenance but the project is at status 0.x -- the consumer SHOULD expect breaking changes (per the README's `Status: 0.x -- expect breaking changes` line) and SHOULD pin the cq version; the consumer SHOULD note the 7-agent install support is documented but the CLI auto-install behavior varies per agent (the README emphasizes `cq install --target <host>` repeated for multi-host setup); the consumer SHOULD note the local-only storage mode keeps KUs on the consumer's machine -- the consumer SHOULD review the local KU directory + the local security model; the consumer SHOULD note the Mozilla.ai hosted cq.exchange mode requires sign-in with GitHub or Google and grants the Mozilla.ai hosted service access to the consumer's KUs.