cap-evolve

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

skillberry-ai/cap-evolve

View on GitHub ↗

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

cap-evolve grew +7.6% in the last 30 days, ranks 782nd of 872 in Evaluation & Guardrails, actively maintained, last commit 3 days ago.

Star trajectory

71 days tracked
2026-09-1171 stars today2026-11-22
Momentum

+7.6% in 30d, above the Evaluation & Guardrails median of +1.4%.

Maintenance

Last commit 3 days ago, fresher than the median of 15d.

How it compares in Evaluation & Guardrails

cap-evolve
71
stars
+7.6% 30d
commit 3 days ago
Evaluation & Guardrails median
235
stars
+1.4% 30d
commit ~15d ago
Leader · impeccable
114.7k
stars
+0.0% 30d
commit today

Ranked 782nd of 872 by stars.

Ranked by shared tags, then keywords, then stars
  1. J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work…

    -15 (-0.5%) in 30d · Committed 69d ago · Python · Apache-2.0

    Shares Agent SDK / Framework, Prompting & Scaffolding, Evaluation & Guardrails, Tools & Integrations

  2. 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project…

    +7 (+2.0%) in 30d · Committed yesterday · Python · MIT

    Shares Agent SDK / Framework, Tools & Integrations, Prompting & Scaffolding, Evaluation & Guardrails

  3. A workflow harness that helps AI coding agents plan, review, test, and ship safer code.

    +2 (+1.0%) in 30d · Committed 72d ago · Shell · Apache-2.0

    Shares Agent SDK / Framework, Prompting & Scaffolding, Evaluation & Guardrails, Tools & Integrations

  4. An inspectable coding agent. Trace changes, diagnose failed runs, and share test evidence. Local-first Python…

    -2 (-1.3%) in 30d · Committed 7d ago · Python · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails, Prompting & Scaffolding, Tools & Integrations

  5. An LLM council that reviews your coding agent's every move

    +1 (+1.0%) in 30d · Committed 208d ago · TypeScript

    Shares Prompting & Scaffolding, Agent SDK / Framework, Evaluation & Guardrails, Tools & Integrations

  6. Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with…

    +159 (+12%) in 30d · Committed 16d ago · Python

    Shares Agent SDK / Framework, Prompting & Scaffolding, Tools & Integrations

  7. OpenLoomi is an open-source AI coworker. It connects your work tools, understands what you’re working on, and…

    +5 (+0.5%) in 30d · Committed 59d ago · TypeScript · Apache-2.0

    Shares Agent SDK / Framework, Tools & Integrations, Prompting & Scaffolding

  8. Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context…

    +6 (+0.6%) in 30d · Committed 38d ago · Go · MIT

    Shares Agent SDK / Framework, Prompting & Scaffolding, Tools & Integrations

  9. Coco Super Intelligence: agent skills, slash commands and subagents for Claude Code, Cursor and Codex. One…

    -616 (-65%) in 30d · Committed today · Python · Apache-2.0

    Shares Agent SDK / Framework, Tools & Integrations, Prompting & Scaffolding

  10. Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for…

    +3 (+1.4%) in 30d · Committed today · Python · MIT

    Shares Agent SDK / Framework, Prompting & Scaffolding, Tools & Integrations

Language
Python
License
Apache License 2.0
Contributors
14
Forks
19
Watchers
1
Open issues
127
Releases
2
Created
2026-06-15
Stars this week
+1

You've seen where cap-evolve stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain cap-evolve?

Claim this page to add your own call-to-action.

Claim this page