AI-native version control in Rust — continuous capture, encrypted knowledge graph, agent governance
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/mahabubul470/gpp && cp gpp/*.md ~/.claude/agents/Subagents overview
# gpp (git++)
[](https://github.com/mahabubul470/gpp/actions/workflows/ci.yml)
[](LICENSE)
[](rust-toolchain.toml)
AI agents change code continuously, then lose the work that happened
between commits — and the notes they keep about your codebase
(`CLAUDE.md`, memory banks, knowledge files) go stale silently when the
code moves on. gpp is a version control system built for that reality: it
**captures every change as it happens**, promotes curated changesets with
intent and provenance, and hosts project knowledge **on the repo's own
history** — so when a commit invalidates something you believed about the
code, gpp can name that commit.

*(Recording is generated by [`scripts/demo.sh`](scripts/demo.sh) —
deterministic, reproducible, no mockups.)*
## 30-second try
```bash
cargo install gpp-cli
gpp init --graphex
echo "fn main() {}" > main.rs
gpp timeline # captured already — no staging, no commit
gpp promote -m "first cut" --intent feature
gpp diff HEAD # semantic diff: renames/moves are one op
```
And the part no other VCS does — record what you believe about the code,
and let history police it:
```bash
gpp belief add --claim "token expiry is 24h" --evidence src/auth.rs:7-7
# ...weeks of commits later...
gpp belief bisect "token expiry is 24h"
# INVALIDATED cs:fhcpef7c "raise token expiry to 7 days"
# - 7 | pub const EXPIRY_HOURS: u64 = 24;
# + 7 | pub const EXPIRY_HOURS: u64 = 168;
```
Deterministic — diff intersection and blob hashes, zero LLM or network
calls. (For scale: asked to *judge* whether a stored memory has been
invalidated, the best frontier model manages 55.2% accuracy on the
[STALE benchmark](https://arxiv.org/abs/2605.06527) — here it's a
history query, not a judgment.) Validated on real history across five
repos in four languages — axum 0.6→0.7, flask 1.1→2.0, clap 3→4, zod
3→4, go-redis 8→9 — where every invalidated belief bisects to a pinned,
documented culprit commit and the control beliefs survive: see
[`demos/belief-bisect/`](demos/belief-bisect/) for the full matrix.
## What makes it different
- **Continuous capture.** A high-frequency timeline records every file
change (SQLite WAL, debounced watcher); curated changesets are
*promoted* from it with an explicit intent, author kind (human/agent),
and cost record. Nothing is lost between commits.
- **Graphex: versioned, encrypted project knowledge.** Architecture,
conventions, decisions, and *beliefs* live in an encrypted knowledge
graph inside the repo, tier-gated per agent trust level, audited on
every read — and staleness-checked against the history it rides on.
- **Agent governance.** First-class agent identity with reputation
scoring, compliance-as-code policies enforced at capture/promote/sync,
anomaly detection, and per-changeset token/cost attribution.
Everything else — P2P sync over Noise, replay, review/RBAC, a relay node,
a TUI — is the platform underneath: see
[`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md).
**Git is the substrate, not the competition.** The bridge
(`gpp git-import` / `git-export` / `git-bridge`) round-trips real Git
commits, so GitHub and existing workflows keep working — gpp's knowledge,
provenance, and governance layers ride alongside. The axum demo above
runs entirely on history imported through this bridge.
## Connect Claude Code (or any MCP client)
gpp ships an MCP server; agents query the knowledge graph (with staleness
flags), propose changesets, and report costs. Drop this in `.mcp.json` at
your repo root:
```json
{
"mcpServers": {
"gpp": { "command": "gpp", "args": ["mcp-server", "--stdio"] }
}
}
```
Full client setup (Claude Desktop, generic stdio) and the exposed tool
list: [`docs/MCP.md`](docs/MCP.md).
## Status
**All 9 roadmap phases (0–8) implemented.** See
[`docs/ROADMAP.md`](docs/ROADMAP.md) for per-phase deliverables and
documented deviations, [`docs/TODO.md`](docs/TODO.md) for the prioritized
backlog, and [`docs/WORKLOG.md`](docs/WORKLOG.md) for the running
engineering log.
Verified 2026-07-12: **177 workspace tests pass**, `cargo clippy` and
`cargo fmt` clean, full workspace builds. No stub crates remain — every
crate has a working implementation. Coverage is measured in CI
(`cargo llvm-cov`; 65.7% line at baseline, being raised).
Test depth is still **uneven**: foundational layers are well covered
(`gpp-core`, `gpp-graphex`, `gpp-diff`, `gpp-tui` ≥ 80% line; the CLI has
end-to-end suites for policy enforcement, cost reporting, reviewer
assignment and belief bisect), while several integration crates remain at
smoke-level (`gpp-sdk`, `gpp-notify`, `gpp-rbac`, `gpp-replay`).
"Implemented" here means *built and tested against its milestone*, not
*exhaustively hardened* everywhere. Closing that gap is the top item in
[`docs/TODO.md`](docs/TODO.md).
## The full layer table
| Layer | Crate | What's implemented |
|---|---|---|
| Storage | `gpp-core` | Content-addressed store (BLAKE3 + zstd), `Blob`/`Tree`, raw verified frame transfer |
| Timeline | `gpp-timeline` | SQLite (WAL) capture, `.gppignore`, debounced watcher, pruning |
| History | `gpp-history` | `Changeset`/`Intent`/`Author`, branch refs, promote, DAG walk |
| Diff | `gpp-diff` | Line + **tree-sitter semantic** diff (Rust/Python/TS/Go), rename/move detection |
| Git bridge | `gpp-git-bridge` | `git-import`/`git-export`/`git-bridge`, SQLite hash map |
| Graphex | `gpp-graphex` | Encrypted (age + AES-GCM) knowledge graph, tier-gated projection, query, lifecycle, audit, **beliefs + staleness engine** |
| SDK / MCP | `gpp-sdk` | `AgentSession`; `gpp mcp-server --stdio` (JSON-RPC MCP) |
| Trust | `gpp-trust` | Reputation scoring, status transitions, overrides, events |
| Policy | `gpp-policy` | `.policy` TOML rules, enforcement at promote (block) + timeline (warn) + sync (block), built-in templates |
| Cost | `gpp-cost` | Per-changeset token/$ records, budgets, efficiency, agent self-reporting |
| Anomaly | `gpp-anomaly` | Scope/burst/size detection, resolution workflow |
| Sync | `gpp-sync` | Noise_XX P2P; objects/refs/policies/graphex; fork-preserve |
| Replay | `gpp-replay` | Reproducible environment snapshots + drift diff |
| Review/RBAC/Notify | `gpp-review` `gpp-rbac` `gpp-notify` | Review lifecycle, roles + branch protection, events/inbox/HMAC webhooks |
| Remote | `gpp-remote` | GitHub/GitLab/Bitbucket PR creation, enriched bodies, CI/review import |
| Relay | `gpp-relay` | Always-on sync hub binary + health endpoint + Dockerfile |
| Clients | `gpp-cli` `gpp-tui` `gpp-deps` | Full CLI, ratatui TUI (`gpp ui`), dependency intel (`gpp deps` + OSV) |
Also: `extensions/{gh-gpp,vscode-gpp,neovim-gpp}`, GitHub Actions +
GitLab CI templates, `deploy/` Docker images, `packaging/` Homebrew.
Documented follow-ups (recorded in the ROADMAP/TODO, not silently
skipped): registry/license APIs for deps, native PyO3/napi bindings,
outbound platform-review sync, apt/dpkg packages.
## Install / build
```bash
cargo install gpp-cli # the `gpp` binary (crates.io)
cargo install gpp-relay # relay node (optional)
# or from a clone
cargo build --release
cargo test --workspace
cargo bench -p gpp-core -p gpp-diff # criterion perf suite
```
Prebuilt binaries for Linux, macOS (ARM + Intel), and Windows are
attached to [each release](https://github.com/mahabubul470/gpp/releases);
`cargo install --git https://github.com/mahabubul470/gpp gpp-cli` tracks
unreleased development.
## More to try
```bash
# Governance
gpp policy template secrets-scan
gpp trust show
gpp audit --include-cost --include-graphex
# Decentralized: sync two repos over Noise
gpp sync serve 127.0.0.1:9473 # on peer A
gpp sync add a 127.0.0.1:9473 && gpp sync # on peer B
# GitHub-compatible
gpp remote setup --platform github --repository acme/webapp
gpp remote pr-create --base main
```
See [`CLAUDE.md`](CLAUDE.md) for project context, [`docs/`](docs/) for the
full specification (architecture, data model, CLI, protocols, roadmap),
and [`docs/book/`](docs/book/) for the user guide + tutorials.
## License
[MIT](LICENSE)
What people ask about gpp
What is mahabubul470/gpp?
+
mahabubul470/gpp is subagents for the Claude AI ecosystem. AI-native version control in Rust — continuous capture, encrypted knowledge graph, agent governance It has 0 GitHub stars and its last recorded update is dated 2026-08-05.
How do I install gpp?
+
You can install gpp by cloning the repository (https://github.com/mahabubul470/gpp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is mahabubul470/gpp safe to use?
+
Our security agent has analyzed mahabubul470/gpp and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains mahabubul470/gpp?
+
mahabubul470/gpp is maintained by mahabubul470. The last recorded GitHub activity is dated 2026-08-05, with 0 open issues.
Are there alternatives to gpp?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy gpp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/mahabubul470-gpp)<a href="https://claudewave.com/repo/mahabubul470-gpp"><img src="https://claudewave.com/api/badge/mahabubul470-gpp" alt="Featured on ClaudeWave: mahabubul470/gpp" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.