by SlanchaAI · MCP Server · ★ 49
Ingot Evidence-gated change control for agent instructions. An agent's skills are instructions it follows. Ingot is a local-first library and MCP server for individual developers who serve versioned skills, evaluate optimizer-generated challengers, and require human promotion before those challengers replace live instructions. SkillOpt integration learns from real agent traces, trains bounded instruction edits, compares them on held-out tasks, and produces an evidence-backed proposal. SkillOpt can propose a change but cannot activate one.
| Stars | 49 |
| Forks | 1 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66.8389265828671/100 |
| Last Updated | 2026-08-20 |
| Created | 2026-07-02 |
| Platforms | docker, mcp, python |
| Est. Tokens | ~16k |
Explore other popular mcp server tools:
ingot is Change management, SkillOpt optimization, and evidence-gated evals for agent skills.. It is categorized as a MCP Server with 49 GitHub stars.
ingot is primarily written in Python. It covers topics such as agent-skills, langgraph, llm-agents.
You can find installation instructions and usage details in the ingot GitHub repository at github.com/SlanchaAI/ingot. The project has 49 stars and 1 forks, indicating an active community.
ingot is released under the Apache-2.0 license, making it free to use and modify according to the license terms.