PenguinHarness, Open, Efficient, Self-Improving Harness

PenguinHarness, an open-source agent framework from Prism Shadow, claims to build agents at 100× the speed of LangChain with a zero-code CLI and Web UI connected to 1000+ models, achieving best accuracy on data analysis at 1/70 of Claude Code's cost. The system uses a minimal toolset tuned for open models like DeepSeek, and its Skills enable agents to self-optimize by running benchmarks and shipping improved versions. A complete RAG app can be generated for $0.02 in tokens on DeepSeek V4 Pro.

With LangChain, you build agents by hand — at 1× speed.With PenguinHarness, agents build agents — at 100×. A zero-code Harness CLI and Web UI, connected to 1000+ models. English | 简体中文 /Prism-Shadow/penguin-harness/blob/main/README.zh.md Three reasons, in deliberate order — from task quality, to how agents get built, to how they keep improving. A deliberately minimal toolset over clean low-level interfaces: fewer tool calls, fewer tokens — deeply tuned for open models like DeepSeek. Each harness on the model it is normally paired with, same tasks, head-to-head: Best accuracy on data analysis — at 1/70 of Claude Code's cost. Type one sentence, and an Agent builds the complete Agent application for you — scaffold, code, and run instructions, end to end: Collect the docs from https://github.com/ericbuess/claude-code-docs and build a RAG app that answers Claude Code questions as a configuration expert, citing its sources. And this is the finished product — a docs expert with retrieval, cited sources that link to the original files, and example questions built in: rag en.mp4 And generating this entire RAG app burned just $0.02 ¥0.2 of tokens — on DeepSeek V4 Pro. With PenguinHarness Skills, an Agent evaluates and optimizes itself: run the benchmark, find the lost points, ship version N+1 — with a snapshot before every round, and every request observable in the Trace view. evo en.mp4 Four Skill groups ship in the box docs https://penguin.ooo/docs/skills ; Agents can also write and optimize their own: | Group | Skills | |---|---| | Office Productivity | data-analysis , firecrawl | | Software Development | web-design , software-engineering | | AI App Development | penguin-sdk , penguin-cli , agenthub-models , vllm , ollama , llamafactory | | Agent Tuning | agent-creation , benchmark-design , agent-evaluation , agent-optimization | | Model | Providers | |---|---| | DeepSeek V4 | DeepSeek, OpenRouter, Fireworks AI, SiliconFlow, Qwen Token Plan | | Kimi K3 | Moonshot AI, OpenRouter, Qwen Pay-As-You-Go | | GLM 5.2 | Z.AI, OpenRouter, Fireworks AI, SiliconFlow, Qwen Token Plan, Qwen Pay-As-You-Go | | Hunyuan 3 | OpenRouter | | Qwen 3.8 Max | Qwen Token Plan preview | | GPT 5.6 | OpenRouter | | Gemini 3.6 Flash | Google Gemini, OpenRouter | | Claude 5 | Anthropic, OpenRouter | Each family's latest generation only — the app's Models page lists every built-in preset, and any OpenAI-protocol endpoint works too: pick a preset, or point a custom endpoint at any of the 1000+ online and local models. | Requirement | Supported | |---|---| | OS | Linux, macOS | | Architecture | x64, arm64 | | Runtime | bundled by the one-line installer npm installs need Node = 24 | | Model | an API key for at least one model | 🚀 Install and launch the full experience multi-session chat, Agent/skill/model management, usage stats, Trace observability, evaluation center : curl -fsSL https://penguin.ooo/install.sh | sh penguin web start the service and open http://127.0.0.1:7364 first login: admin / penguin-2026 📦 Or via npm: npm install -g @prismshadow/penguin-cli . Configure models on the in-app Models page, then chat. The same engine, scriptable — made to be driven by agents and agents building agents : penguin config model add --provider deepseek --model-id deepseek-v4-pro --api-key sk-... --set-default penguin run -m "Create hello.txt containing Hello, Penguin" one-shot task penguin chat interactive REPL /compact, /exit, Ctrl-C to interrupt penguin server headless service same API the Web App uses js import { createAgent, isCompleteModelMessage, userText } from "@prismshadow/penguin-core"; const agent = await createAgent { agentId: "default agent" } ; const session = await agent.createSession { workspaceDir: process.cwd } ; for await const output of session.run userText "Create hello.txt containing hi" , { approve: async = "allow", // per-tool-call approval } { if isCompleteModelMessage output && output.payload.type === "text" { console.log output.payload.text ; } } - Public release of the benchmark suite - Desktop app - Windows support - Agent company and templates - Company-level self evolving - OpenShell integration permission-governed shell - More to come… pnpm install && pnpm build build first: core's exports point at dist/ pnpm dev backend + web app together prefixed logs, deps built once See CONTRIBUTING.md /Prism-Shadow/penguin-harness/blob/main/CONTRIBUTING.md for the full workspace guide: dev commands, quality gates, repo layout, and the changelog rule. If you use PenguinHarness in your research, please cite: @software{penguinharness2026, author = {{PrismShadow Team}}, title = {PenguinHarness: Efficient Self-Improving Harness for Everyone}, year = {2026}, url = {https://github.com/Prism-Shadow/penguin-harness}, license = {Apache-2.0} } Apache-2.0 /Prism-Shadow/penguin-harness/blob/main/LICENSE © 2026 Prism Shadow Built with ❤️ by Yaowei Zheng https://github.com/hiyouga author of LlamaFactory https://github.com/hiyouga/LlamaFactory , the PrismShadow AI Team https://github.com/Prism-Shadow , and Fable 5 https://www.anthropic.com/news/claude-fable-5-mythos-5 .