Claude Code Agents, Compared
Compatibility here means full support, read from each agent's own AGENTS.md and documentation rather than inferred from the fact that it is an agent. Agents that only partly work under Claude Code are left out on purpose — a partial listing is the kind that costs you an afternoon.
| # | Agent | FARS | Trust | Stars | License | Language | Last commit |
|---|---|---|---|---|---|---|---|
| 1 | QuantDinger AI Trading OS | 89 | 25/25 | 11.3k | Apache-2.0 | Python | 2026-09-02 |
| 2 | Unlazy Completion Discipline | 86 | 25/25 | 3.0k | MIT | JavaScript | 2026-08-29 |
| 3 | Better Harness | 85 | 23/25 | 2.1k | MIT | JavaScript | 2026-09-02 |
| 4 | LLM Wiki | 85 | 24/25 | 1.2k | MIT | Python | 2026-08-27 |
| 5 | JS Reverse MCP | 82 | 21/25 | 2.7k | Apache-2.0 | TypeScript | 2026-08-25 |
| 6 | NotebookLM Python Automation | 81 | 21/25 | 19.1k | MIT | Python | 2026-09-02 |
| 7 | Kungfu | 81 | 18/25 | 4.5k | Apache-2.0 | C++ | 2026-09-02 |
| 8 | git-lrc Commit-Time Code Review | 80 | 24/25 | 1.5k | NOASSERTION | Go | 2026-08-24 |
| 9 | Chrome DevTools MCP | 79 | 17/25 | 50.6k | Apache-2.0 | TypeScript | 2026-09-02 |
| 10 | Gortex Code Intelligence | 78 | 21/25 | 1.5k | Apache-2.0 | Go | 2026-09-02 |
| 11 | Bernstein | 78 | 19/25 | 1.1k | Apache-2.0 | Python | 2026-09-02 |
| 12 | Apify MCP Server | 77 | 16/25 | 5.7k | MIT | TypeScript | 2026-09-02 |
The order is the FARS total; stars only break ties, because popularity measures attention rather than whether something holds up. Two limits are worth knowing before you read the order. These are static reviews — source, documentation and repository metadata, with no runtime reproduction — which caps reliability, effectiveness and verifiability and puts the achievable maximum at 77 rather than 100. And a gap of a few points sits inside the noise of that method. Read the table as a shortlist worth investigating, not as a verdict; every score links to its full dimension breakdown and the evidence behind it. Review method →
1. QuantDinger AI Trading OS
Turn AI-assisted market research into Python strategies, backtests, paper trading, live execution, and monitoring.
Where it differs
Unlike a black-box signal service, QuantDinger keeps strategy code, risk settings, credentials, and deployment under the operator's control. Unlike a design tied to one model vendor, it documents OpenRouter, OpenAI-compatible APIs, Google, DeepSeek, Grok, MiniMax, and custom endpoints, although each still requires its own configuration and service access. The base Compose stack also differs from an always-on monitoring bundle: Prometheus, Grafana, and Alertmanager are optional through the observability overlay.
2. Unlazy Completion Discipline
Keep AI agents from finishing early with deep decomposition, acceptance ledgers, and executable gates.
3. Better Harness
Diagnose and improve coding-agent workflows with verifiable evidence.
4. LLM Wiki
Compile multi-agent research, sources, and session memory into durable, queryable topic wikis.
5. JS Reverse MCP
Continuous browser-side JavaScript debugging and replay for AI coding assistants.
Where it differs
Unlike exposing the Chrome DevTools API to a model unchanged, JS Reverse MCP groups scripts, breakpoints, traffic, WebSockets, state, and local files into primitives for sustained analysis. The default Patchright mode uses the installed Google Chrome and retains access to the Web Store, extensions, and sync; --cloak instead uses a CloakBrowser binary with C++-level fingerprint patches but no Google services or Web Store. The project positions anti-detection as support for the debugging chain, not as a general-purpose crawling framework.
6. NotebookLM Python Automation
Automate Gemini Notebook research, generation, and exports through Python, CLI, or coding agents.
Where it differs
Compared with the Gemini Notebook web interface, notebooklm-py emphasizes scripted control and local extraction. It supports batch downloads, structured quiz and flashcard exports, mind-map JSON, CSV data tables, source full text, individual slide revision, and programmatic sharing. That additional reach comes with greater maintenance risk because the client relies on undocumented endpoints rather than an official Google SDK.
7. Kungfu
Keep one body of work moving across agents, sessions, and failures.
Where it differs
Compared with manually copying chats and re-explaining decisions when moving among Codex, Claude, OpenCode, or Amp, Kungfu keeps the Work objective, evidence, progress, and Attempt history outside those sessions. It complements rather than replaces these agents, and its TUI and GUI are optional sidecar views rather than substitutes for native agent consoles.
8. git-lrc Commit-Time Code Review
Automatically review Git diffs and surface risks before each commit lands.
Where it differs
Compared with PR review, git-lrc moves feedback to the pre-commit stage, before faulty code is committed, pushed, and handed to teammates. Compared with an IDE extension, it uses Git commit as an editor-independent trigger shared by the team. The bundled claude-lrc provides natural-language and slash-command control inside Claude Code, while git-lrc supplies cross-editor commit-time enforcement. LiveReview is the named team-oriented extension of the product, adding dashboards, organization-level policies, and review analytics.
9. Chrome DevTools MCP
Give coding agents direct Chrome automation, debugging, and performance analysis.
Where it differs
Full mode targets deep debugging with automation, performance, network, console, and optional specialist categories; --slim exposes only navigation, script execution, and screenshots for basic browser work and a smaller tool surface. The MCP server is intended for structured integration with compatible coding clients, while the included CLI covers use without MCP. Launching a dedicated Chrome profile provides separation from everyday browsing, whereas attaching to an existing Chrome preserves logins and manual testing state at the cost of greater data-exposure risk.
10. Gortex Code Intelligence
A local code graph that gives coding assistants precise context and cross-repository impact analysis.
11. Bernstein
Deterministically orchestrate parallel CLI coding agents with offline-verifiable run records.
12. Apify MCP Server
Let AI assistants discover and run Apify Actors for web extraction and structured data collection.
Where it differs
The hosted https://mcp.apify.com endpoint is the preferred delivery mode because it supports OAuth, current hosted-only features, dynamic access to rental Actors, and Streamable HTTP. Local stdio is useful for desktop and command-line integrations but has a narrower feature boundary. The legacy /sse endpoint has been removed, so existing configurations must migrate by dropping /sse. For agentic payments, AGI is the recommended option and issues a prepaid, spend-capped Apify token usable with any Actor; direct x402 uses USDC on Base and Skyfire uses PAY tokens, but both are restricted to Pay Per Event Actors and do not support Standby Actors.