Stars
ctx-wire runs your commands, compresses the output with declarative filters, scrubs secrets, and hands your agent a short result. The full log stays on disk for when something actually fails. Cut t…
TypeScript SDK for Claude Code - spawn, stream, and control the CLI programmatically
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Heavily compressed docker images for SWE Bench Verified
Download and parse data from Garmin Connect or a Garmin watch, FitBit CSV, and MS Health CSV files into and analyze data in Sqlite serverless databases with Jupyter notebooks.
We track and analyze the activity and performance of autonomous code agents in the wild
[NeurIPS 2024] Evaluation harness for SWT-Bench, a benchmark for evaluating LLM repository-level test-generation
Guardrails for secure and robust agent development
Qodo-Cover: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞
The easiest, and fastest way to run AI-generated Python code safely
Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.
SWE-bench: Can Language Models Resolve Real-world Github Issues?
Primary Kite repo — private bits replaced with XXXXXXX
Labels and other data for the paper "Are we done with ImageNet?"
Monotone operator equilibrium networks
VNN Neural Network Verification Competition 2021
The Udacity open source self-driving car project