Initialize repository with harness code and assets
Initial import of all source code, config, and README assets: the packages workspace (cli, core, server, web, docs, landing, skills), build scripts, tooling config, and CI workflows. Includes the data-layout revision made on this branch: the local data root defaults to ~/.penguin/data (PENGUIN_HOME still overrides; the installer keeps its binaries in ~/.penguin), and every Agent lives under <project>/agents/<agent>/ — path helpers, the three agent-enumeration scans, the system prompt, built-in Skills, tests and docs all follow the new layout. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018ihk8iQuo3kv2aPjAYEPuR
This commit is contained in:
Yaowei ZhengandClaude Opus 4.8 authored and GitHub committed
1 parent
056bed7aeb
commit
45bfae6e94
543 files changed
+92949
No files matched your search
@@ -0,0 +1,71 @@
|
||||
---
|
||||
title: "Introducing PenguinHarness: agents that build agents"
|
||||
date: 2026-07-17
|
||||
category: news
|
||||
excerpt: The first open-source harness with recursive self-improvement is here — lightweight, efficient and secure infrastructure covering everything from automatic agent construction to continuous self-evolution.
|
||||
---
|
||||
|
||||
Today we are releasing **PenguinHarness** — an open-source harness built for constructing and evolving agents. Its purpose fits in one line:
|
||||
|
||||
> Efficient Self-Improving Harness for Everyone.
|
||||
|
||||
## Why PenguinHarness
|
||||
|
||||
Over the past year the way agent applications are built has been converging fast: what really decides quality is not a heavyweight framework but a simple, reliable, observable harness. PenguinHarness is rebuilt from the ground up — no dependency on any agent framework, a fully open-source self-developed kernel — and it brings three things to the open-source world first:
|
||||
|
||||
- **Simplest Is the Best**: a deliberately minimal toolset over clean low-level interfaces — fewer tool calls, fewer Tokens, complex tasks done efficiently.
|
||||
- **Harness for Building Agents**: with the PenguinHarness SDK, an Agent builds complete Agent applications for you, autonomously, from scratch.
|
||||
- **Harness for Recursive Self-Improvement**: with PenguinHarness Skills, an Agent evaluates and optimizes itself, improving recursively over time.
|
||||
|
||||
For the latter two, PenguinHarness is the first open-source implementation in the industry.
|
||||
|
||||
## Same model, equal or better quality, lower cost
|
||||
|
||||
All runs use the same DeepSeek V4 Pro model, head-to-head against Claude Code and OpenAI Codex on two suites (per-run means below).
|
||||
|
||||
Complex data analysis (15 tasks, single run):
|
||||
|
||||
| Framework | Model | Accuracy (%) | Tokens (M) | Cost ($) |
|
||||
| --- | --- | ---: | ---: | ---: |
|
||||
| PenguinHarness | DeepSeek V4 Pro | 66.7 | 18.04 | 0.552 |
|
||||
| Claude Code | DeepSeek V4 Pro | 66.7 | 21.17 | 0.641 |
|
||||
| OpenAI Codex | DeepSeek V4 Pro | 46.7 | 13.36 | 0.427 |
|
||||
|
||||
Coding tasks (40 tasks × 2 runs averaged, thinking high, 30 min per-case timeout, CNY pricing converted at $1 = ¥7):
|
||||
|
||||
| Framework | Model | Accuracy (%) | Tokens (M) | Cost ($) |
|
||||
| --- | --- | ---: | ---: | ---: |
|
||||
| PenguinHarness | DeepSeek V4 Pro | 50.00 | 2.10 | 0.041 |
|
||||
| Claude Code | DeepSeek V4 Pro | 48.75 | 2.00 | 0.048 |
|
||||
| OpenAI Codex | DeepSeek V4 Pro | 42.50 | 2.65 | 0.043 |
|
||||
|
||||
On the data-analysis suite PenguinHarness ties Claude Code on accuracy and clearly beats OpenAI Codex while using 14.8% fewer Tokens at 13.8% lower cost; on the coding suite it scores highest of the three at the lowest per-run cost.
|
||||
|
||||
## Evolution within bounds, security first
|
||||
|
||||
The biggest worry about self-improvement is losing control. PenguinHarness answers with a contract — CONTRACT.md:
|
||||
|
||||
- Evolution is strictly confined to Workspace and Skills; the harness core security boundary is never modified.
|
||||
- Tool calls run only after approval, and every approval is audited.
|
||||
- Risky changes snapshot first — every step of evolution can be rolled back.
|
||||
- Fully open source and locally deployable: data never leaves your machine, meeting enterprise security requirements.
|
||||
|
||||
## Get started now
|
||||
|
||||
Install with one command (Linux / macOS, x64 / arm64, bundled Node runtime):
|
||||
|
||||
```bash
|
||||
curl -fsSL https://github.com/Prism-Shadow/penguin-harness/releases/latest/download/install.sh | sh
|
||||
```
|
||||
|
||||
Configure a model (DeepSeek as an example), run your first task, or open the desktop-grade web interface with `penguin web`:
|
||||
|
||||
```bash
|
||||
penguin config model add --model-id deepseek-v4-pro --api-key sk-your-key --set-default
|
||||
penguin run --approve allow-all --message "Analyze data.csv and summarize quarterly sales"
|
||||
penguin web
|
||||
```
|
||||
|
||||
PenguinHarness supports 1000+ online and local models and multi-agent collaborative evolution, and runs on as little as a single CPU. Through continuous evolution it makes complex AI development ever simpler — a more efficient, more reliable, lower-hallucination and lower-cost Agent productivity engine.
|
||||
|
||||
Follow us on [GitHub](https://github.com/Prism-Shadow/penguin-harness) and open your first issue.
|
||||
@@ -0,0 +1,71 @@
|
||||
---
|
||||
title: PenguinHarness 正式发布：让 Agent 为你构建 Agent
|
||||
date: 2026-07-17
|
||||
category: news
|
||||
excerpt: 首个支持递归自我进化的开源 Harness 正式发布——以轻量、高效、安全的方式，提供从 Agent 自动构建到持续自我进化的完整基础设施。
|
||||
---
|
||||
|
||||
今天，我们正式发布 **PenguinHarness**——一个为构建与进化 Agent 而生的开源 Harness。它的主旨只有一句话：
|
||||
|
||||
> Efficient Self-Improving Harness for Everyone.
|
||||
|
||||
## 为什么是 PenguinHarness
|
||||
|
||||
过去一年里，Agent 应用的开发范式在快速收敛：真正决定效果的不是庞大的框架，而是一个简洁、可靠、可观测的 Harness。PenguinHarness 从底层重构，不依赖任何 Agent 框架，开源自研 Harness 内核，并率先把三件事带入开源世界：
|
||||
|
||||
- **Simplest Is the Best**：坚持最小化工具集与简洁的底层接口，以更少的工具调用与 Token 消耗，高效完成复杂任务。
|
||||
- **Harness for Building Agents**：通过 PenguinHarness SDK，让 Agent 从零自主完成 Agent 应用的构建。
|
||||
- **Harness for Recursive Self-Improvement**：通过 PenguinHarness Skills，Agent 以自我评估与自我优化实现递归式自我提升。
|
||||
|
||||
后两项能力，PenguinHarness 是业内首个开源实现。
|
||||
|
||||
## 同一模型，同级效果，更低消耗
|
||||
|
||||
全部使用同一 DeepSeek V4 Pro 模型，与 Claude Code、OpenAI Codex 在两套题库上正面对比（表中为单次运行均值）。
|
||||
|
||||
复杂数据分析（15 题，单次运行）：
|
||||
|
||||
| 实验框架 | 模型名称 | 准确率（%） | Token 用量（M） | 成本（$） |
|
||||
| --- | --- | ---: | ---: | ---: |
|
||||
| PenguinHarness | DeepSeek V4 Pro | 66.7 | 18.04 | 0.552 |
|
||||
| Claude Code | DeepSeek V4 Pro | 66.7 | 21.17 | 0.641 |
|
||||
| OpenAI Codex | DeepSeek V4 Pro | 46.7 | 13.36 | 0.427 |
|
||||
|
||||
代码任务（40 题 × 2 runs 取均值，thinking high、单题 30 分钟超时，人民币计价按 $1 = ¥7 折算）：
|
||||
|
||||
| 实验框架 | 模型名称 | 准确率（%） | Token 用量（M） | 成本（$） |
|
||||
| --- | --- | ---: | ---: | ---: |
|
||||
| PenguinHarness | DeepSeek V4 Pro | 50.00 | 2.10 | 0.041 |
|
||||
| Claude Code | DeepSeek V4 Pro | 48.75 | 2.00 | 0.048 |
|
||||
| OpenAI Codex | DeepSeek V4 Pro | 42.50 | 2.65 | 0.043 |
|
||||
|
||||
数据分析套件与 Claude Code 准确率持平、显著超过 OpenAI Codex，同时 Token 消耗少 14.8%、成本低 13.8%；代码套件三者中准确率最高、单次成本最低。
|
||||
|
||||
## 进化有界，安全先行
|
||||
|
||||
自我进化最大的疑虑是失控。PenguinHarness 用一份契约（CONTRACT.md）回答这个问题：
|
||||
|
||||
- 进化严格限制在 Workspace 与 Skill 之内，不修改 Harness 核心安全边界；
|
||||
- 工具调用先经批准，每次批准皆留审计；
|
||||
- 风险修改之前先留版本快照，任何一次进化都可回退；
|
||||
- 完全开源、本地部署，数据不出域，满足企业级数据安全。
|
||||
|
||||
## 现在就可以开始
|
||||
|
||||
一行命令安装（Linux / macOS，x64 / arm64，内嵌 Node 运行时）：
|
||||
|
||||
```bash
|
||||
curl -fsSL https://github.com/Prism-Shadow/penguin-harness/releases/latest/download/install.sh | sh
|
||||
```
|
||||
|
||||
配置模型（以 DeepSeek 为例）后即可运行第一个任务，或用 `penguin web` 打开桌面级 Web 界面：
|
||||
|
||||
```bash
|
||||
penguin config model add --model-id deepseek-v4-pro --api-key sk-your-key --set-default
|
||||
penguin run --approve allow-all --message "分析 data.csv，输出各季度销售额汇总"
|
||||
penguin web
|
||||
```
|
||||
|
||||
PenguinHarness 支持 1000 多种在线与本地模型、多智能体协作进化，最低单 CPU 即可运行。通过不断进化，它会让复杂的 AI 开发越来越简单——为你提供更高效、更可靠、更低幻觉、更低成本的 Agent 生产力引擎。
|
||||
|
||||
欢迎在 [GitHub](https://github.com/Prism-Shadow/penguin-harness) 上关注我们，提出你的第一个 Issue。
|
||||
@@ -0,0 +1,30 @@
|
||||
---
|
||||
title: "July 2026 updates: scheduled tasks, Agent snapshots and a stronger evaluation center"
|
||||
date: 2026-07-17
|
||||
category: changelog
|
||||
excerpt: Scheduled tasks, Agent State snapshots with export/import, benchmark scoreboards, the model identity principle and one-line install have all landed on main.
|
||||
---
|
||||
|
||||
This month a batch of updates directly serving "stable evolution" landed on main. Highlights below.
|
||||
|
||||
## Scheduled tasks & Agent State snapshots
|
||||
|
||||
- **Scheduled tasks**: one TOML file per task under `agent_state/schedule/` — cron-style scheduling keeps Agents working autonomously around the clock.
|
||||
- **Agent State snapshots with export/import**: `system_config.yaml` carries a `version`; risky changes (optimization passes, import overwrite) snapshot to `snapshots/v<version>.tar.gz` first, restore any time, with the live vault preserved.
|
||||
|
||||
## Evaluation center
|
||||
|
||||
- **Benchmark scoreboards**: bundled suites, per-case scoring and trend curves; evaluations are charted per model, and each run deep-links to its Session's trace view.
|
||||
- **Evaluations carry the model**: the model reference moved from benchmark_config onto each evaluation (`provider` / `model_id` as a pair), making cross-model comparison direct.
|
||||
|
||||
## Model system
|
||||
|
||||
- **Model identity principle**: a model is uniquely identified by the `(provider, model_id)` pair; connection details live inline on the Project config entry, with client-resolved environment-variable fallback when the credential is left empty.
|
||||
- **Custom provider groups**: beyond built-in vendors and custom, users can create their own groups (OpenAI protocol by default, base URL required).
|
||||
- **Runtime baseline raised to Node ≥ 24**: bundled runtime, CI and the release pipeline all migrated.
|
||||
|
||||
## Install & experience
|
||||
|
||||
- **One-line install**: a repo-root `install.sh` — `curl | sh` detects Linux / macOS and x64 / arm64; artifacts bundle the Node runtime, unpack and run.
|
||||
- **Skill library revamp**: Skills now use files as the runtime source of truth, with redesigned cards and quick invocation; built-in Agents converge to a single default_agent, with agent creation/optimization fully carried by the Skill library.
|
||||
- **Stability fixes**: Gemini tool_call_id collisions on consecutive same-name calls, stream-view scroll jitter on short containers, and WorkGroup parallel tool timing are all fixed.
|
||||
@@ -0,0 +1,30 @@
|
||||
---
|
||||
title: 2026 年 7 月更新：定时任务、Agent 快照与评估中心增强
|
||||
date: 2026-07-17
|
||||
category: changelog
|
||||
excerpt: 定时任务调度、Agent State 版本快照与导出导入、Benchmark 记分展示、模型确定原则与一键安装等一批更新已合入主干。
|
||||
---
|
||||
|
||||
本月主干合入了一批与「稳定进化」直接相关的更新，摘要如下。
|
||||
|
||||
## 定时任务与 Agent State 快照
|
||||
|
||||
- **定时任务调度**：`agent_state/schedule/` 下每个任务一个 TOML 文件，计划调度让 Agent 全天候自主执行。
|
||||
- **Agent State 版本快照与导出导入**：`system_config.yaml` 以 `version` 标识当前版本，风险修改（优化类修改、导入覆盖）前自动快照到 `snapshots/v<version>.tar.gz`，可随时回退，且恢复时保留现行 vault。
|
||||
|
||||
## 评估中心增强
|
||||
|
||||
- **Benchmark 记分展示**：内建题库、逐题评分与趋势曲线，评估记录按模型分系列展示，run 可直达对应 Session 的轨迹观测。
|
||||
- **评估携带模型**：模型引用从 benchmark_config 移到每条 evaluation（`provider` / `model_id` 成对记录），跨模型对比更直观。
|
||||
|
||||
## 模型体系
|
||||
|
||||
- **模型确定原则**：模型由 `(provider, model_id)` 二元组唯一确定，连接信息内联在 Project 配置的模型条目上；credential 留空时按 client 解析结果回退环境变量。
|
||||
- **模型页自建分组**：内置厂商分组与 custom 之外，支持用户自建分组（OpenAI 协议缺省、base URL 必填）。
|
||||
- **运行基线升级 Node ≥ 24**：内嵌运行时同步更新，CI 与发布链路完成迁移。
|
||||
|
||||
## 安装与体验
|
||||
|
||||
- **一键安装**：仓库根新增 `install.sh`，`curl | sh` 识别 Linux / macOS 与 x64 / arm64，产物内嵌 Node 运行时，解压即用。
|
||||
- **技能库改版**：Skill 以文件为运行时真源，技能卡片改版并支持快捷调用；内置 Agent 收敛为 default_agent，Agent 构建与优化能力全部由技能库承载。
|
||||
- **稳定性修复**：Gemini 连续同名工具调用 tool_call_id 冲突、流式输出短滚动区上滑抖动、WorkGroup 并行工具用时统计等问题已修复。
|
||||
Reference in new issue
Block a user