- visualize can draw a neighbourhood instead of the whole repository. The
- crossreposearchtool accepts repos, a list of registry aliases or
- querygraphtool resolves dotted targets such as
- update and buildorupdategraphtool report files that failed to
- CRGHOOKWORKTREES=1 keeps the generated pre-commit hook active inside
- CRGDISCOVERYTIMEOUT bounds each Git command that discovers what
Code Review Graph by Tirth Kanani
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Recently added on Oct 10, 2026. The description, category and pricing were filled in from public metadata and have not been checked by an editor yet.
Price
Free (OSS)
free and open source
Popularity
#21 in Agent tooling
Gid Score 40 / 100 · #122 of 378 overall
Trend
Slowing down
usage down 24.4% over 30 days
Development
Updated recently
latest 2.3.9, 22d ago
Community
32K GitHub stars
67.3K package downloads a week
What Code Review Graph does
Key facts
| Maker | Tirth Kanani |
|---|---|
| First released | February 2026 |
| License | MIT |
| Main language | Python |
| Open issues and PRs | 177 |
Pricing
Open source under the MIT licence; check the website for any paid hosted plans.
, checked Oct 10, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (MIT)
- Closest alternativeOpenShell · all alternatives
Get started with Code Review Graph
| PyPI | pip install code-review-graph |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer.
Code Review Graph alternatives
Best Code Review Graph alternatives compared · All agent tooling for cost, context and memory
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | ||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 6 |
OpenShellNVIDIA Corporation |
76 | 89.4K | up 76.9% | up 201.3% | — | 15.6K+159/day | 0.1.3yesterday | Free (OSS) | ||
| 11 |
|
73 | 23M | up 4.0% | — | — | 60.4K+61/day | 1.104.22d ago | Free (OSS) | ||
| 15 |
NemoClawNVIDIA Corporation |
68 | — | — | — | — | 22.7K+10/day | — | Free (OSS) | ||
| 19 |
|
63 | 2.4M | down 14.8% | up 0.1% | — | 190K+354/day | 2.11.03mo ago | Free + $16/mo | ||
| 20 |
|
63 | 8.4M | up 2.7% | up 5.5% | — | 35.6K+39/day | 4.55.02d ago | Free (OSS) | ||
| 27 |
|
60 | 3.4M | down 9.1% | up 20.5% | — | 14.2K+22/day | 2.53.14d ago | Free + $150/mo | ||
| No agents match that filter. | |||||||||||
Ratings from people who use Code Review Graph
No ratings yet. Used Code Review Graph? Rate it and say what it is good and bad at.
Code Review Graph news
-
74 agents added to AgentGid
Symphony, OpenShell, Codex Security, NemoClaw, Agent Browser, Opensre, Caveman, Brag, Open Code Review, Understand-Anything, Codegraph, BrowserSkill and 62 more
What changed: recent Code Review Graph releases
3 stable releases in the last 90 days · Full changelog
- OS watches are no longer registered inside ignored trees, so a Maven target/ or a large nodemodules cannot exhaust the inotify budget (#811).
- Deleting and recreating a watched directory (rm -rf src && mkdir src, or two ordinary git checkouts) is recognized as a replaced directory rather than a dead watcher, on filesystems that change…
- A repository reached through a symlinked path is watched and indexed instead of silently dropping every event, through both watch --repo and serve --auto-watch (#892).
- code-review-graph forget PATH ... drops already-parsed files without a full rebuild.
- uninstall --platform NAME unbinds a single platform and leaves the rest intact.
- A Voyage AI embedding provider, and embeddings persisted after every batch so an interrupted cloud run keeps its progress (#783).
- expanded CLI-first workflows, CommonJS parsing, quiet/JSON output, enrichment, and dead-code analysis
- broader Terraform, Ansible, VB.NET, SystemVerilog, Rust, PHP/Laravel, Julia, Python, C#, Java, Spring, and WebFlux graph coverage
- bounded transitive test coverage, churn risk, weighted impact ranking, graph provenance, documentation-aware embeddings, and safe JSON export
- safer uninstall and platform configuration, including CodeBuddy and official OpenCode contracts
- hardened MCP concurrency, daemon lifecycle, Windows process handling, Git path parsing, ignore rules, community detection, and visualization layout
- updated supported dependency and GitHub Action versions, plus secure fork-PR review handling
- Custom languages without forking (#320): drop a .code-review-graph/languages.toml into your repo to index any grammar shipped by tree-sitter-language-pack. See docs/CUSTOMLANGUAGES.md.
- GitHub Action for risk-scored PR reviews: builds/restores the graph from CI cache and posts a sticky review comment with risk table, affected flows, test gaps, and token savings. See…
- Honest benchmarks: new agentbaseline benchmark (graph vs a realistic grep-and-read agent), failed eval runs excluded from aggregates instead of inflating them, non-circular co-change ground truth…
- docs/FAQ.md: vs LSP, vs RAG, vs agentic grep, when NOT to use this tool, and how to verify it's working.
- Windows: daemon status WinError 87 crash (#511) and CLI detect-changes mapping 0 functions
- storefilebatch transaction guard (#489 — community PR
- 🪟 Token Savings panel on both code-review-graph detect-changes --brief and the new code-review-graph update --brief. Per-category breakdown (Functions / Tests / Risk / Other) that sums exactly to…
- ✅ --verify flag cross-checks the displayed numbers against OpenAI's cl100kbase tokenizer. Calibration shows the estimate stays within +0.5% of real GPT-4 tokens in aggregate across 222…
- 🔁 Deterministic eval pipeline — pinned upstream SHAs, full clones with returncode checks, fixed Leiden seed. Two contributors running the benchmark recipe on different machines on different days…
- 🎯 Multi-hop retrieval benchmark + richer embedding text + identifier-aware search boost lift compound-query accuracy from 0.545 → 0.909.
- 📦 code-review-graph embed CLI subcommand for explicit embedding generation. Previously only reachable via MCP.
- Estimated context savings metadata for graph-filtered review/impact/architecture responses. The new contextsavings field is intentionally compact (estimated, savedtokens, savedpercent) and uses…
- CLI estimated savings line for code-review-graph detect-changes --brief; full JSON output includes the same compact contextsavings metadata.
- Architecture overview is compact by default: getarchitectureoverviewtool now defaults to detaillevel="minimal", dropping per-community member lists and aggregating cross-community edges by…
- Bounded change analysis: detectchangestool can now cap very large changed-function and transitive-test frontiers with CRGMAXCHANGEDFUNCS and CRGMAXTRANSITIVEFRONTIER, and can return a structured…
- Windows semantic search deadlock (#508/#507): local embedding models are pre-warmed on the main thread on Windows before FastMCP starts worker dispatch.
- Rust test detection (#503/#502): Rust #[test] and common async test attributes now produce Test nodes.
Code Review Graph popularity and usage data
Code Review Graph was downloaded 67.3K times from PyPI in the week ending Oct 8, 2026, down 9.2% on the week before and down 24.4% over the last 30 days compared with the 30 before. The GitHub repository has 32K stars, 834 of them added in the last 30 days. The latest stable release is 2.3.9, published Sep 18, 2026; there were 1 stable releases in the past 30 days.
Download the raw daily series: code-review-graph.csv
Gid Score breakdown
Adoption41
Community63
Attention—
Momentum26
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
Code Review Graph FAQ
How much does Code Review Graph cost?
Open source under the MIT licence; check the website for any paid hosted plans.
Is Code Review Graph open source?
Yes. Code Review Graph is open source, released under the MIT license.
How popular is Code Review Graph?
Code Review Graph was downloaded 67.3K times from PyPI in the week ending Oct 8, 2026, down 9.2% on the week before and down 24.4% over the last 30 days compared with the 30 before. The GitHub repository has 32K stars, 834 of them added in the last 30 days. The latest stable release is 2.3.9, published Sep 18, 2026; there were 1 stable releases in the past 30 days.
What is the latest version of Code Review Graph?
The latest stable release we track is 2.3.9, published on Sep 18, 2026.
What are the alternatives to Code Review Graph?
The closest alternatives in the same category by Gid Score are OpenShell, LiteLLM, NemoClaw, Firecrawl.
For the makers of Code Review Graph badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/code-review-graph/)[](https://agentgid.com/agents/code-review-graph/)[](https://agentgid.com/agents/code-review-graph/)Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
PyPI: code-review-graph. GitHub: tirth8205/code-review-graph. Site rank: code-review-graph.com on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: code-review-graph.com, github.com, pypi.org.