h5i logo
VERSION CONTROL · AI-READY · OPEN SOURCE

Next-Gen AI-Aware Git

h5i (pronounced high-five) is a Git sidecar that extends version control for teams where AI agents write production code alongside humans. Where Git answers what changed, h5i answers who, why, whether it was safe, and how to undo it.

cargo install --git https://github.com/Koukyosyumei/h5i h5i-core
5
SEMANTIC DIMENSIONS
14
FEATURES
12
INTEGRITY RULES
0
API CALLS FOR HANDOFF

Everything you need to audit AI code

One sidecar. Zero lock-in. Works alongside any Git workflow.

h5i commit --prompt … --audit
AI-tagged commits
Stores the exact prompt, model, agent ID, and test results alongside every commit in refs/h5i/notes.
h5i blame <file>
AI-aware blame
Per-line authorship enriched with agent name, model, and test badge — line or AST mode.
h5i log
Enriched log
Full AI provenance inline — prompt, model, agent, test badge — in a readable timeline.
h5i rollback "the OAuth changes"
Intent rollback
Reverts a commit by matching your description against stored prompts. No hash needed.
h5i commit --audit
Integrity audit
12 deterministic rules — no AI in the audit path — checking credential leaks, CI/CD tampering, scope creep, and eval() patterns.
h5i notes footprint
Session footprint
Maps which files the AI read vs. edited per session — surfaces implicit dependencies.
h5i notes uncertainty
Uncertainty heatmap
Every moment the AI hedged, with the exact quote, confidence score, and file-level risk map.
h5i notes churn
File churn
Edit-to-read ratio per file — high-churn code gets flagged for extra review automatically.
h5i notes graph
Intent graph
Visualises the causal chain across commits — which AI commit triggered which downstream change.
h5i context init / trace / commit
Context workspace
Version-controlled notepad (goal, OTA trace, milestones) in refs/h5i/context — survives session resets.
h5i resume
Session handoff
Ready-to-paste briefing — goal, progress, risky files, suggested opening prompt — from local data. No API call.
h5i memory snapshot / diff
Memory tracking
Snapshots Claude's memory files at every commit and diffs them across versions in refs/h5i/memory.
h5i push / pull
Team sharing
Syncs all AI metadata (refs/h5i/*) to/from the remote in one command — teammates see full provenance.
h5i serve
Web dashboard
Browser UI with Timeline, Summary, Integrity, Intent Graph, Memory, and Sessions tabs at localhost:7150.

See h5i in action

Real workflows where h5i adds signal that Git alone can't provide.

01
Find who wrote this — and with what prompt
Per-line AI authorship, model, and the exact prompt that produced it.
~/my-project
$ h5i blame src/auth.rs

STAT COMMIT   AUTHOR/AGENT    | CONTENT
  a3f9c2b  claude-code     | fn validate_token(tok: &str) -> bool {
    a3f9c2b  claude-code     |     tok.len() == 64 && tok.chars().all(|c| c.is_ascii_hexdigit())
       9eff001  alice           | }

$ h5i log --limit 1

commit a3f9c2b...
Author:  Alice <alice@example.com>
Agent:   claude-code (claude-sonnet-4-6) ✨
Prompt:  "add per-IP rate limiting to the auth endpoint"
Tests:   ✔ 42 passed, 0 failed, 1.23s [pytest]

    implement rate limiting
02
Keep Claude's context alive across sessions
A version-controlled notepad in refs/h5i/context that survives session resets.
~/my-project
# Project start — run once
$ h5i context init --goal "Build an OAuth2 login system"

# During the session — record reasoning
$ h5i context trace --kind OBSERVE "Redis p99 latency is 2 ms"
$ h5i context trace --kind THINK   "40 MB overhead is acceptable"
$ h5i context trace --kind ACT     "Switching session store to Redis"

# After a milestone
$ h5i context commit "Implemented token refresh flow"

# New session — restore state instantly
$ h5i context show --trace

── Context ──────────────────────────────────────────────────
  Project: Build an OAuth2 login system  (branch: main)

  Milestones
    ✔ [x] Initial setup
    ○ [ ] Token refresh flow

  Recent Trace
    [14:22:01] ACT:     Switching session store to Redis
    [14:21:44] THINK:  40 MB overhead is acceptable
    [14:21:30] OBSERVE: Redis p99 latency is 2 ms
03
Audit what the integrity engine caught
12 deterministic rules — no AI in the audit path.
~/my-project
$ h5i commit -m "refactor auth module" --audit

⚠ INTEGRITY WARNING (score: 0.70)
  ⚠ [UNDECLARED_DELETION]  247 lines deleted (72% of total changes)
                           with no deletion intent stated.
  ℹ [CONFIG_FILE_MODIFIED] Configuration file 'config/auth.yaml' modified.

Commit anyway with --force, or revise your changes.
04
Understand what Claude actually did in a session
Footprint, uncertainty heatmap, and file churn — all from the session log.
~/my-project
$ h5i notes uncertainty

── Uncertainty Heatmap ───────────────────────────────────────────
  7 signals  ·  session 90130372  ·  3 files

  Risk Map
  src/auth.rs       ████████████░░░░  ●●●  4 signals  avg  28%
  src/main.rs       ██████░░░░░░░░░░  ●●   2 signals  avg  40%
  src/server.rs     ██░░░░░░░░░░░░░░    1 signal   avg  52%

  Signals
  ██  t:32    not sure       src/auth.rs   [ 25%]
       "…token validation might break if the token contains special chars…"

  ▓▓  t:220   let me check   src/main.rs   [ 45%]
       "…The LSP shows the match still isn't seeing the new arm…"
05
Start the next session with full situational awareness
No API call needed — every field comes from locally stored h5i data.
~/my-project
$ h5i resume

── Session Handoff ──────────────────────────────────────────────
  Branch: feat/oauth  ·  Last active: 2026-03-27 14:22 UTC
  Agent: claude-code  ·  Model: claude-sonnet-4-6
  HEAD: a3f9c2b  implement token refresh flow

  Progress
     Initial setup
     GitHub provider integration
    ○ Token refresh flow  ← resume here
    ○ Logout + session cleanup

  ⚠ High-Risk Files
    ██████████  src/auth.rs     4 signals  churn 80%  "not sure"
    ██████░░░░  src/session.rs  2 signals  churn 60%  "let me check"

  Suggested Opening Prompt
  ────────────────────────────────────────────────────────────────
  Continue building "Build an OAuth2 login system". Completed so
  far: Initial setup, GitHub provider integration. Next milestone:
  Token refresh flow. Review src/auth.rs before editing — 4
  uncertainty signals recorded there in the last session.
  ────────────────────────────────────────────────────────────────

Browse everything in one place

Run h5i serve to open a local dashboard at http://localhost:7150.

h5i web dashboard — Timeline tab

Timeline tab — every commit with full AI context, test badge, integrity score, and one-click re-audit.
Additional tabs: Summary · Integrity · Intent Graph · Memory · Sessions

Up and running in two commands

INSTALL

# Install from source cargo install \ --git https://github.com/Koukyosyumei/h5i \ h5i-core # Init in your project cd your-project h5i init

FIRST COMMIT

# Commit with AI metadata + audit h5i commit \ -m "add rate limiting" \ --prompt "add per-IP rate limit" \ --model claude-sonnet-4-6 \ --agent claude-code \ --audit

PUSH TO TEAM

# Push all h5i refs + code h5i push git push origin main # Teammates fetch and see # full AI provenance in h5i log

OPEN DASHBOARD

# Browse AI history in browser h5i serve # → http://localhost:7150 # Generate session handoff h5i resume

Ready to trust your AI-generated code?

h5i gives every AI commit an audit trail, an author, and an undo button. Apache 2.0. No lock-in.