# AutoContext — Self-Improving Agent Harness

> AutoContext adds iterative improvement loops, provider integrations, MCP access, and CLI workflows so coding-agent results improve across repeated runs.

## Install

Copy the content below into your project:

## Quick Use

```bash
uv tool install autocontext==0.5.0
AUTOCONTEXT_AGENT_PROVIDER=pi AUTOCONTEXT_PI_COMMAND=pi autocontext --help
pi install npm:pi-autocontext
```

## Intro

AutoContext adds iterative improvement loops, provider integrations, MCP access, and CLI workflows so coding-agent results improve across repeated runs.

**Best for:** teams experimenting with recursive improvement loops and provider-agnostic agent evaluation instead of one-shot prompt runs

**Works with:** uv, Pi runtime, Claude Code MCP setups, multiple model providers, CLI and MCP-based agent workflows

**Setup time:** 8-15 minutes

### Key facts (verified)

- GitHub: 983 stars · 83 forks · pushed 2026-05-13.
- License: Apache-2.0; owner avatar verified from GitHub API for greyhaven-ai.
- Entry point checked from README: `uv tool install autocontext==0.5.0`.

## Main

AutoContext is best read as a harness layer, not a single prompt package. Its job is to loop on scenarios, evaluate outputs, and feed improvements back into the next agent pass.

That matters when teams have moved past hobby usage and need repeatable improvement instead of ad hoc intuition about why a run succeeded.

The README gives two practical integration modes: CLI-first with Pi or provider env vars, and MCP-first inside Claude Code. That flexibility is a strong sign the project was built for real usage, not just demos.

### Source-backed notes

- README offers a 30-second path with `uv tool install autocontext==0.5.0`.
- It documents provider-based operation for Anthropic, OpenAI, Gemini, Mistral, Groq, OpenRouter, Azure, Claude CLI, Codex CLI, and MLX.
- Pi runtime and Claude Code MCP integration are both called out as supported paths.

### FAQ

**Q: Is AutoContext tied to one model provider?**
A: No. The README documents several providers plus Claude CLI, Codex CLI, and MLX paths.

**Q: What is the fastest install path?**
A: `uv tool install autocontext==0.5.0`, then point it at Pi or another supported provider.

**Q: Why use it?**
A: It helps repeated agent runs improve systematically instead of starting from scratch every time.

## Source & Thanks

> Source: https://github.com/greyhaven-ai/autocontext
> License: Apache-2.0
> GitHub stars: 983 · forks: 83

---

<!-- ZH -->

## Quick Use

```bash
uv tool install autocontext==0.5.0
AUTOCONTEXT_AGENT_PROVIDER=pi AUTOCONTEXT_PI_COMMAND=pi autocontext --help
pi install npm:pi-autocontext
```

## Intro

AutoContext 通过迭代改进循环、Provider 集成、MCP 接入与 CLI 工作流来包裹编码 agent，让提示词与结果能在重复运行中持续变好。

**Best for:** 希望把一次性 prompt 试错升级为可迭代改进循环、并且需要多 provider 兼容的团队

**Works with:** uv、Pi runtime、Claude Code MCP 配置、多模型提供商、CLI 与 MCP 型 agent 工作流

**Setup time:** 8-15 minutes

### Key facts (verified)

- GitHub：983 stars · 83 forks；最近更新 2026-05-13。
- 许可证：Apache-2.0；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中核对过的入口命令：`uv tool install autocontext==0.5.0`。

## Main

AutoContext 更像 harness 层，而不是一份单独 prompt。它的核心工作是围绕场景做循环评估，把改进结果继续反馈给下一轮 agent。

这对已经过了玩具阶段的团队很关键：你需要的是可重复改进，而不是靠经验猜测某次运行为什么成功。

README 给出了两条可执行集成路径：基于 Pi 或 provider 环境变量的 CLI 路径，以及 Claude Code 里的 MCP 路径。这说明它面向的是实际工作流，而不只是 demo。

### Source-backed notes

- README offers a 30-second path with `uv tool install autocontext==0.5.0`.
- It documents provider-based operation for Anthropic, OpenAI, Gemini, Mistral, Groq, OpenRouter, Azure, Claude CLI, Codex CLI, and MLX.
- Pi runtime and Claude Code MCP integration are both called out as supported paths.

### FAQ

**问：Is AutoContext tied to one model provider?**
答：No. The README documents several providers plus Claude CLI, Codex CLI, and MLX paths.

**问：What is the fastest install path?**
答：`uv tool install autocontext==0.5.0`, then point it at Pi or another supported provider.

**问：Why use it?**
答：It helps repeated agent runs improve systematically instead of starting from scratch every time.

## Source & Thanks

> Source: https://github.com/greyhaven-ai/autocontext
> License: Apache-2.0
> GitHub stars: 983 · forks: 83


---
Source: https://tokrepo.com/en/workflows/autocontext-self-improving-agent-harness
Author: Agent Toolkit