#66th of 38 in Agent and MCP starters
penguin-harness
Agent framework that evolves an agent's prompts, skills and tools against benchmarks
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
3 on 14 Jul 20262,895 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
PenguinHarness runs agents with a small toolset and keeps the model fixed while it evolves the harness (prompts, Skills, tools, hooks) over scored rounds. Five RSI algorithms (default, OPRO, APE, ACE, AWM) ship as plugins and run on built-in Harbor benchmarks in Docker, with each candidate snapshotted as a version. It ships as a desktop app, Web App, CLI and TypeScript SDK, and can also generate agent apps from a prompt.
Who it is for: Engineers tuning agent prompts and skills, or self-hosting agents
Strengths
- Five RSI algorithms run on the same benchmarks, scoreboard and per-version snapshots
- Desktop app, Web App, CLI and SDK share one engine and the ~/.penguin/data directory
- Works with many providers plus custom OpenAI-protocol endpoints, including local models
- Agents can run on remote machines over ssh and drive Chrome through an extension
Weaknesses
- Benchmarks run as Harbor tasks in Docker, so self-evolution needs Docker
- Cost and accuracy claims come from the project's own suite, not independent runs
- RAM and disk requirements are not documented
- Company-level self-evolution and OpenShell integration are still unchecked roadmap items
What it needs
- TypeScript, OpenAI, Anthropic, Google Gemini, OpenRouter
- Needs Node >= 24 (npm install), Docker (benchmarks), Model provider API key
- Docker
- env example file
Also in Agent and MCP starters
See all 38| Rank | Project | Score |
|---|---|---|
| 1 | deepseek-harnessPlugin-based agent harness from DeepSeek with a local Web UI | 70 out of 100 |
| 2 | mcp-typescript-templateTypeScript starter for remote MCP servers over HTTP with Express and Effect | 63 out of 100 |
| 3 | docker-agentDocker CLI plugin that runs multi-agent teams defined in YAML | 60 out of 100 |
| #4 | mcp-useTypeScript framework for building MCP servers with React Views and an Inspector | 59 out of 100 |
| #5 | computerDurable Object virtual filesystem with container, shell and JavaScript runtimes for agents | 59 out of 100 |