Stars
Split information output of pwndbg output
A C-based Kernel / CPU side-channel exploit development library.
A minimal Linux kernel development & exploitation lab.
A Prometheus exporter for Celery metrics
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Unified high-performance Python client for object and file stores.
A Datacenter Scale Distributed Inference Serving Framework
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
Module, Model, and Tensor Serialization/Deserialization
A user-space file system for interacting with Google Cloud Storage
CTF Archives: Collection of CTF Challenges.
[NeurIPS 2024] Evaluation harness for SWT-Bench, a benchmark for evaluating LLM repository-level test-generation
Harbor is a framework for running agent evaluations and creating and using RL environments.
An extremely fast Python package and project manager, written in Rust.
Inspect: A framework for large language model evaluations
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
A guidance language for controlling large language models.
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
Parses cron schedules to iterate over datetime objects.
Fast and memory-efficient exact attention