The leading open-source AI copilot for JetBrains. Connect to any model in any environment, and customize your coding experience in any way you like.
- intellij
- intellij-plugin
- jetbrains
- codellama
132,241 visible repositories in the index
25–48 of 95 · Most stars
The leading open-source AI copilot for JetBrains. Connect to any model in any environment, and customize your coding experience in any way you like.
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.
Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Llama 2 Everywhere (L2E)
Evaluate Agent Skills and environments. Evolve Skills with evidence.
BrowserGym, a Gym environment for web task automation
Welcome to the Ollama Docker Compose Setup! This project simplifies the deployment of Ollama using Docker Compose, making it easy to run Ollama with all its dependencies in a containerized environment
Secrets of RLHF in Large Language Models Part I: PPO
An alignment auditing agent capable of quickly exploring alignment hypothesis
Evaluate and improve models and agents using environments
KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
The repository host gives no description.
🔒 Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get fine-grained access control and monitoring per user, application, or environment. Supports OpenAI, Azure OpenAI, Anthropic, vLLM, and open-source LLMs.
A non-saturating, open-ended environment for evaluating LLMs in Factorio
Read it. See it. Get it. Built at GDG AI Hack Milan 2026 for "Learn Different" track.
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
sentence embedding by Smooth Inverse Frequency weighting scheme
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
The repository host gives no description.
AndroidWorld is an environment and benchmark for autonomous agents