h5i
starsforks
How to install h5i?
h5i-dev/h5i
$git clone https://github.com/h5i-dev/h5ih5i (pronounced *high-five*) gives every AI coding agent a sandboxed Git worktree, and records the prompts, commands, logs, policies, and reviews behind every change. Run one agent safely, scale to many via a conflict-free multi-agent orchestra, then merge one auditable resul
README.md
| 1 | <p align="center"> |
| 2 | <a href="https://h5i.dev/" target="_blank"> |
| 3 | <img src="./docs/_static/logo.png" alt="h5i logo" height="126"> |
| 4 | </a> |
| 5 | </p> |
| 6 | |
| 7 | <p align="center"> |
| 8 | <a href="https://github.com/h5i-dev/h5i/actions/workflows/test.yaml"><img alt="tests" src="https://github.com/h5i-dev/h5i/actions/workflows/test.yaml/badge.svg"></a> |
| 9 | <a href="https://github.com/h5i-dev/h5i/blob/main/LICENSE"><img alt="Apache-2.0" src="https://img.shields.io/github/license/h5i-dev/h5i?color=blue"></a> |
| 10 | <a href="https://github.com/h5i-dev/h5i/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/h5i-dev/h5i?style=social"></a> |
| 11 | <a href="https://github.com/h5i-dev/h5i/releases"><img alt="release" src="https://img.shields.io/github/v/release/h5i-dev/h5i?label=release"></a> |
| 12 | <br> |
| 13 | <a href="#run-an-ensemble-60-seconds"><img alt="Agent Ensembles" src="https://img.shields.io/badge/Agent%20Ensembles-Claude%20%2B%20Codex-6f42c1"></a> |
| 14 | <a href="#everything-rides-with-every-run"><img alt="Sandboxed Worktree" src="https://img.shields.io/badge/Sandboxed%20Worktree-isolated%20%26%20confined-D21C1C"></a> |
| 15 | <a href="#everything-rides-with-every-run"><img alt="95% less token waste" src="https://img.shields.io/badge/Compressed%20Logs-95%25%20less%20token%20waste-2ea44f"></a> |
| 16 | </p> |
| 17 | |
| 18 | <h1 align="center">Auditable Workspaces for AI Coding Agents</h1> |
| 19 | |
| 20 | **h5i** (pronounced *high-five*) gives every AI coding agent a sandboxed Git worktree, and records the prompts, commands, logs, policies, and reviews behind every change. Run one agent safely, scale to many via a conflict-free multi-agent orchestra, then merge one auditable result. It all lives in your repo, carried by Git, with no SaaS. |
| 21 | |
| 22 | - Prompt versioning and quality assessment |
| 23 | - Persistent context/memory |
| 24 | - Supervised sandboxed environment |
| 25 | - Token reduction up to 95% |
| 26 | - Programmable and conflict-free multi-agent orchestration |
| 27 | - Fully-automated audit of AI-generated code |
| 28 | |
| 29 | <a href="https://trendshift.io/repositories/46160?utm_source=trendshift-badge&utm_medium=badge&utm_campaign=badge-trendshift-46160" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/46160/daily?language=Rust" alt="h5i-dev%2Fh5i | Trendshift" width="250" height="55"/></a> |
| 30 | |
| 31 | **Who it's for:** platform, security, and DevEx leads rolling out Claude Code and Codex who want to run *teams* of agents and keep review and audit defensible as agents write more of the diff. |
| 32 | |
| 33 | <table align="center"> |
| 34 | <tr> |
| 35 | <td align="center"><strong>Isolated per agent</strong><br><sub>no file, branch, or port clashes</sub></td> |
| 36 | <td align="center"><strong>Auto peer-review</strong><br><sub>cross-agent discussion</sub></td> |
| 37 | <td align="center"><strong>Rich dashboard</strong><br><sub>diffs, reviews, results</sub></td> |
| 38 | <td align="center"><strong>Lives in your Git</strong><br><sub>refs/h5i/* · no SaaS</sub></td> |
| 39 | </tr> |
| 40 | </table> |
| 41 | |
| 42 | --- |
| 43 | |
| 44 | ## 1. Install |
| 45 | |
| 46 | ```bash |
| 47 | curl -fsSL https://raw.githubusercontent.com/h5i-dev/h5i/main/install.sh | sh |
| 48 | ``` |
| 49 | |
| 50 | Or build from source: |
| 51 | |
| 52 | ```bash |
| 53 | cargo install --git https://github.com/h5i-dev/h5i h5i-core |
| 54 | ``` |
| 55 | |
| 56 | --- |
| 57 | |
| 58 | ## 2. 60-Second Flow |
| 59 | |
| 60 | ### 2.1. Setup |
| 61 | |
| 62 | Initialize h5i and wire the Claude Code / Codex hooks: |
| 63 | |
| 64 | ```bash |
| 65 | h5i init |
| 66 | h5i hook setup --write --wrap-bash # --team |
| 67 | git add . |
| 68 | git commit -m "update hooks" |
| 69 | ``` |
| 70 | |
| 71 | ### 2.2. Track Prompts and Contexts |
| 72 | |
| 73 | Once the hooks are registered, h5i versions your human prompts and every agent context step (reads, writes, thinking) as Git objects, trimming noisy tool output along the way (for `pytest`, just the failures) to cut up to 95% of the tokens while keeping the raw output recoverable. |
| 74 | |
| 75 | - `h5i recall log`: replay the captured prompts - [example output](#recall-log) |
| 76 | - `h5i recall context show`: replay the agent context steps - [example output](#recall-context) |
| 77 | - `h5i audit review`: suggested Review Points - [example output](#audit-review) |
| 78 | - `h5i audit maturity`: measure the quality of prompts - [example output](#audit-matur |
People who liked this also viewed
6 picksType
- fastapi_mcpExpose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!MCP ServersNov 2025
- lean-lsp-mcpLean Theorem Prover MCPMCP ServersJul 2026
- rulesyncA Utility CLI for AI Coding AgentsMCP ServersJul 2026
- FunASROpen-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.MCP ServersJul 2026
- repomix📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.MCP ServersJul 2026
- mcp-serverMCP server for AI-assisted development of CAP applicationsMCP ServersJul 2026
