greyhaven-ai/autocontext

Registry

Summary

AutoContext is a recursive self-improving harness that equips AI agents—including Claude, Codex, and Hermes—with dynamic context management to autonomously succeed on any task.

Key features

• Recursive self-improving architecture for agent autonomy
• Dynamic context management across multiple AI models
• Seamless integration with Claude, Codex, and Hermes agents
• Designed for zero-shot task success without manual intervention

Use cases

• Automating complex multi-step research workflows
• Enabling AI agents to self-correct and iterate on tasks
• Building autonomous coding assistants with persistent context
• Powering recursive problem-solving in AI agent pipelines

README excerpt

<!-- autocontext-readme-hero:start --> <p align="center"> <img src="autocontext/assets/banner.svg" alt="autocontext ASCII banner" style="max-width: 100%; height: auto;" /> </p> <p align="center"><strong>a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task</strong></p> <p align="center"> <a href="https://github.com/greyhaven-ai/autocontext/blob/main/LICENSE"><img src="https://img.shields.io/github/license/greyhaven-ai/autocontext" alt="License"></a> <a href="https://github.com/greyhaven-ai/autocontext/stargazers"><img src="https://img.shields.io/github/stars/greyhaven-ai/autocontext" alt="GitHub stars"></a> <a href="https://github.com/greyhaven-ai/autocontext/commits/main"><img src="https://img.shields.io/github/last-commit/greyhaven-ai/autocontext" alt="Last commit"></a> <a href="https://pypi.org/project/autocontext/"><img src="https://img.shields.io/pypi/v/autocontext" alt="PyPI version"></a> <a href="https://www.npmjs.com/package/autoctx"><img src="https://img.shields.io/npm/v/autoctx" alt="npm version"></a> </p> <!-- autocontext-readme-hero:end --> Autocontext is a harness. You point it at a goal in plain language. It iterates against real evaluation, keeps what worked, throws out what didn't, and produces a structured trace of the work plus the artifacts, playbooks, datasets, and (optionally) a distilled local model that the next agent inherits. Repeated runs get better, not just different. ## Try It In 30 Seconds The fastest path uses our **Pi runtime**, a local coding agent that handles its own auth. No API key plumbing, no provider config: install Pi, install autocontext, point one at the other. ```bash uv tool install autocontext==0.5.0 AUTOCONTEXT_AGENT_PROVIDER=pi \ AUTO

Topics