Self-evolving plugin
Linter / framework that writes PRs against itself when it observes new patterns.
5 primary frameworks · 5 lower-confidence entries
313+ skills for 12 AI tools covering engineering, marketing, C-level advisory, compliance, research, and finance — all from one canonical skill library.
Implements Harness Engineering as a Go-binary-installed Claude Code environment with auto-TDD/DDD methodology selection, 20-event hook coverage, self-evolving…
Prevent context loss, scattered development, and forgotten lessons through a generation-based lifecycle where AI and human co-evolve a typed knowledge base…
Gives MCP-capable coding agents a local contract-lifecycle harness with governance audits and explicit completion gates.
Build self-improving AI agent teams via a supervised training loop: specialist agents advise, a meta-agent evolves prompts based on human feedback, and an…
Show 5 lower-confidence entriestier-b · tier-c · unknown · delta reports
These entries map to § a18 by tag but carry weaker evidence — fewer documented primitives, delta reports of absent skills, or marketing-only sites without a public repo. They're listed for completeness; treat them with appropriate caution.
Thin, self-healing CDP harness connecting an LLM to the user's real Chrome browser with coordinate-first clicking and agent-written helper code that improves it…
Production-grade CLI for Karpathy's LLM Wiki pattern: ingests any content into a local-first durable markdown wiki + knowledge graph with MCP server, approval q…
Treats NL artifacts (skills, agents, commands, CLAUDE.md) as lintable programs with a 50-rule rubric, penalty-based scoring, NL-TDD, and a self-evolving exempla…
Provides a 12-rule drop-in CLAUDE.md behavior baseline (building on Karpathy's 4-rule original) that addresses agent-orchestration failures: token spirals, sile…
Provide a self-improving, cross-platform plugin ecosystem where skills evolve through eval-gated iteration rather than human-written intuition.