self-improvement
- @metaharness/darwinReleased5d agoVersion0.7.0
Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench Lite code-repair — 7.7% open-loop -> 58.3% via cheap->frontier tiering (official swebench Docker, verified), ~$0.01-$0.74/instance vs $1-20 for frontier agents; (2) Darwin Shie
- @okasputra/agent-primeReleasedyesterdayVersion1.9.0
Generate project-specific, cross-harness coding-agent guidance (AGENTS.md, skills, safety hooks) for any repo. Zero-dependency Node.
- paperthinReleasedyesterdayVersion0.6.0
Plain-Markdown skills that turn old engineering wisdom into reflexes your agent reaches for on its own — on any agent.
- evomap-opencode-pluginReleased4d agoVersion0.1.0
Official EvoMap Evolver plugin for OpenCode: persistent, auditable agent evolution memory powered by GEP.
- ninja-terminalsReleased6d agoVersion2.4.9
MCP server for multi-terminal Claude Code orchestration with DAG task management, parallel execution, and self-improvement
- @plune-ai/cairnReleased5d agoVersion0.5.0
Cairn — an AI that walks your system and leaves a trail of tests. Autonomous QA agent (UI today; API/unit/docs planned) powered by Claude/OpenRouter, with self-improvement via Langfuse.
- @phuetz/code-buddyReleased3d agoVersion1.6.1
Open-source multi-provider AI coding agent for the terminal, desktop, and HTTP. 15 LLM providers (Grok, Claude, ChatGPT, Gemini, Ollama, LM Studio, …) with ~110 tools, a peer-to-peer fleet, opt-in self-improvement, multi-channel messaging, and a skills sy
- @tangle-network/agent-runtimeReleased2d agoVersion0.79.2
Shared task-lifecycle skeleton for agents: a recursive loop kernel for chat turns, one-shot tasks, and multi-attempt loops, with trace capture and eval-gated self-improvement. Domain behavior lives in adapters; scoring and ship-gates in @tangle-network/ag