by greyhaven-ai · Codex Skill · ★ 1.0k
turn repeated agent work into validated, reusable execution autocontext is a system for running scenarios, tasks, and missions, analyzing what happened, and carrying forward the knowledge that actually improved outcomes. The North Star is to move from one-off frontier-model exploration toward workflows that become more reliable, more auditable, and cheaper to run over time.
| Stars | 1,016 |
| Forks | 77 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 50.892/100 |
| Open Issues | 2 |
| Last Updated | 2026-05-22 |
| Created | 2026-02-11 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~1507k |
These tools work well together with autocontext for enhanced workflows:
Explore other popular codex skill tools:
autocontext is a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task. It is categorized as a Codex Skill with 1.0k GitHub stars.
autocontext is primarily written in Python. It covers topics such as agents, ai, autoresearch.
You can find installation instructions and usage details in the autocontext GitHub repository at github.com/greyhaven-ai/autocontext. The project has 1.0k stars and 77 forks, indicating an active community.
autocontext is released under the Apache-2.0 license, making it free to use and modify according to the license terms.