By koloai
Trace Python code execution for AI agents by capturing functions, return values, local variables, HTTP requests, and SQL queries into greppable trace files, enabling runtime debugging and data inspection via search.
[!TIP] Kolo v3 is here Trace data as plain text files, searchable by humans and agents alike. See what's new.
Trace and visualize your Python code.
Screenshot of Kolo from the Todo Demo app
Getting started with Kolo only takes a couple of minutes. The fastest way to understand what Kolo does and how it can be helpful is by trying it out on a codebase you work on. But if you're in a hurry or can't try Kolo on your own codebase, you can preview some functionality in our playground.
Trace a Django request for inspection, visualization, and debugging purposes.
pip install kolo"kolo.middleware.KoloMiddleware" to the top of your MIDDLEWARE list in settings.pypython manage.py runserver and make a request to any page.localhost:8000/_kolo/ to view your traced request. It should look similar to the screenshot at the top of the page 🚀(For a more in-depth version of this tutorial see How to: Trace Django requests)
If you have any questions or trouble getting set up with Kolo, please get in touch with us. We're here to help and would love any feedback!
What Kolo looks like when used with a real world Django application (Simple Poll)
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub koloai/kolo --plugin koloAdd Logfire observability to Python applications with auto-instrumentation for FastAPI, httpx, asyncpg, SQLAlchemy, and more
PHP debugging and analysis tools using Xdebug. Trace execution, step debug, profile performance, and analyze code coverage.
Automatic tracing of Claude Code sessions to Arize AX or Phoenix with OpenInference spans. Supports 9 hooks for comprehensive observability.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.