by oooscoos
Benzi is a compiler-backed coding agent that compiles your codebase into a resolved, queryable map of calls, data flow, control flow and class hierarchy first; then it reads, explains, runs, edits and verifies your code using it. Includes a runtime tracer that settles what static analysis can't. The Benzi compiler also works as an MCP server.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
# Add to your Claude Code skills
git clone https://github.com/oooscoos/BenziGuides for using ai agents skills like Benzi.
Last scanned: 10/3/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-10-03T09:41:35.637Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how Benzi compares with popular alternatives.
What is Benzi — how it works in one paragraph Live demos — StallionSwipe, VS Code's own source, or any repo you paste What people say — what people wrote about it SWE-bench Verified — 391/500 (78.2%) for $37.33 How it works — compile, query, edit, verify Tools — 16 of the 35+ the index makes possible What the index actually changes — lines read vs three other harnesses Features · Language support · Getting started FAQ — privacy, API keys, pricing, limits
Most AI coding agents dump a repo into a context window and hope the model finds what matters. Benzi parses every file first — a real compiler, built on tree-sitter — into a precise, queryable map. Every symbol, every call edge, every reference, every class in its inheritance chain. One pass, done.
Every file parsed, imports resolved, class ancestry built, every identifier traced to its definition — before a single question is answered. Call flow and data flow join at every call site, so a bad value traces to its origin in one tool call. Claude Code greps; Cursor embeds; Aider maps signatures; Benzi resolves — in O(1). Ten languages so far, plus a markup engine for HTML, CSS, and DOM-JS — see Language support.
You can try pasting this repo's link to Benzi in the live demo too!
StallionSwipe · Python, HTML, CSS, JS — a dating app for horses, greenfielded by Benzi from scratch in a single chat session. No image is a file: every horse portrait is procedural SVG, generated in code. Match with one and it flirts back through a real model, live. Frontend, backend, and the prompts — all written by Benzi. Try it live.
VS Code's own source, resolved · TypeScript — the real microsoft/vscode repo is 1.8M lines; this indexes 923k of them: the editor core (src/vs/editor + src/vs/base), the platform services layer, and workbench's shell/API/browser plumbing — deliberately excluding the 747k-line grab-bag of individual features in workbench/contrib. Built once, in just over two minutes, then cached. Try it live (chat panel, near the bottom of the page).
Or, try any repo of your choice at all here — point Benzi at any public GitHub repo and it builds the index live. varianttech.net/demo.
"78.2% for $37 is a slap in the face to the 'brute force wins' school." — Alex Xiang, zicode (translated)
"Benzi is proving that the core competency of coding tools is shifting from simple 'reading comprehension' to 'structural grasping ability.'" — Gi Pyeong Lee, Tech Blog
"Fewer tokens, no context drift. Wild idea, honestly." — prompt 🤖 AI News
"It analyzes changes before writing them — and beats Claude Code on benchmarks." — Ponte al dIA (translated)
The full SWE-bench Verified set — 500 real GitHub issues from twelve Python repositories — run end to end on DeepSeek v4-flash, one attempt per instance, graded by the official swebench.harness.run_evaluation inside its own per-instance Docker images, with network access to GitHub and PyPI blocked inside every container.
| Resolved | 391 / 500 — 78.2% |
| Total cost, all 500 instances | $37.33 |
| Cost per instance resolved | $0.095 |
| Source lines read (total / median) | 231,574 / 379 |
| Model turns (total / median) | 16,091 / 27 |
| Input tokens served from cache | 97% |
| Output tokens | 22.0M |
Full technical report: swebench/SWE_BENCH_REPORT.md (web version). Every instance's cost, tokens, turns, and lines read: varianttech.net/benchmark_swebench. The cross-harness efficiency comparison below (and the full 24-bug chart): varianttech.net/benchmark.
profile, get_callers, backflow, trace_path, skim_source, ~30 more.A sample of 16 of Benzi's 35+ tools — what falls out of actually resolving the code, from the index itself to the gates on every write.
| Tool | What
Benzi is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by oooscoos. Benzi is a compiler-backed coding agent that compiles your codebase into a resolved, queryable map of calls, data flow, control flow and class hierarchy first; then it reads, explains, runs, edits and verifies your code using it. Includes a runtime tracer that settles what static analysis can't. The Benzi compiler also works as an MCP server. It has 126 GitHub stars.
Yes. Benzi passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/oooscoos/Benzi" and add it to your Claude Code skills directory (see the Installation section above).
Benzi is primarily written in Python. It is open-source under oooscoos on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Benzi against similar tools.
No comments yet. Be the first to share your thoughts!