{"repo":"iLearn-Lab/EvoHarness","free":true,"listed":false,"github":"https://github.com/iLearn-Lab/EvoHarness","clone":"git clone https://github.com/iLearn-Lab/EvoHarness.git","description":"EvoHarness delivers terminal-native agent infrastructure: tools, commands, skills, agents, plugins, MCP, memory, approvals, and controlled self-evolution","language":"Python","stars":58,"topics":["claude-code","evo","evolution","evolutionary-algorithms","harness","harness-engineering"],"license":null,"category":"mcp-servers","readme_excerpt":"English ZH-CN EvoHarness delivers terminal-native agent infrastructure: tools, commands, skills, agents, plugins, MCP, memory, approvals, and controlled self-evolution. Build with the project: shape an open, visible, and research-grade harness for coding workflows. 🧠✨ Controlled Self-Evolution (- -) 🌌 Evidence, operators, candidate patches, and promotion paths 🩵 EvoHarness treats self-evolution as control over the harness surface , not as unconstrained agent autonomy. The real question is not \"can the model rewrite itself once,\" but: - 🧾 when to evolve : use real sessions, traces, failures, approvals, and workspace state as evidence - 🎛️ which operator to choose : revise command , revise skill , distill memory , grow ecosystem , or stop - 🛑 when not to evolve : low-value changes should be filtered before mutation - ✅ how changes enter the runtime : candidate patches must pass validation, then get promoted, held, or rolled back So the loop can be read in one line: evidence - operator choice - candidate patch - validation - promote / hold / rollback In short, EvoHarness studies self-evolution as a long-horizon operator-control problem over commands, skills, agents, plugins, MCP, memory, and policy surfaces. 🐴 Three-stage mascot evolution: saddle - harness - elegant evolution ✨🩵 --- 🧩🛠️ Harness Architecture \\(^ ^)/ 🧩 One runtime core • 👀 visible harness surfaces • 🧠 one long-horizon state layer EvoHarness is built around one architectural bet: the harness should be ","default_branch":null,"files":null,"tree":[],"storefront":"/r/iLearn-Lab","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/iLearn-Lab/EvoHarness/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}