Discover

Every project in the index. Underrated first: good projects that haven’t been noticed yet.

26 projects

#llm-evaluation

Harvey LAB
Benchmark tasks and harness for testing AI agents on legal work
Agent frameworks and tools AI models and runtimes
1.5k
stable-worldmodel
Python toolkit for collecting data, training, and evaluating world models
AI models and runtimes Education
2.3k
SIA
Self-improvement loop that rewrites an AI agent to score higher on a benchmark
Agent frameworks and tools AI models and runtimes
2.2k
Marin
Open research platform for training large language models end to end
AI models and runtimes Education
4k
Switchyard
Per-request model routing for AI agents across cheap and capable LLMs
AI models and runtimes Agent frameworks and tools
3.4k
UltraRAG
MCP-based framework for building and evaluating RAG pipelines in YAML
Agent frameworks and tools AI models and runtimes
5.7k
Apache Maka
Local-first agent workspace that logs every model call and tool action
AI coding agents Agent frameworks and tools
5.9k
whichllm
Command-line tool that ranks local LLMs that will run on your hardware
AI models and runtimes Developer tools
andy6.8k
OBLITERATUS
Toolkit for locating and removing refusal directions in open LLMs
AI models and runtimes
pliny8.9k
MiroThinker
Open-weight deep research agent models with a tool-using search framework
AI models and runtimes Agent frameworks and tools
8.4k
Hugging Face Skills
Agent skill pack for working with the Hugging Face Hub and ML workflows
Agent skills and plugins AI models and runtimes
11.2k
Superhuman
DeepMind datasets and benchmarks for olympiad-level math reasoning in AI
AI models and runtimes Education
809
OpenSRE
Framework and CLI for building AI agents that investigate incidents
Servers and infrastructure Agent frameworks and tools
12.3k
ADR
Detection, telemetry, and benchmarking for securing enterprise AI agents
Privacy and security Agent frameworks and tools Security testing and OSINT
2.1k
AlpaSim
Closed-loop simulator for testing end-to-end self-driving policies
Hardware and IoT Education AI models and runtimes
1.3k
G0DM0D3
Multi-model AI chat interface for jailbreak and red-team research
AI apps Security testing and OSINT
pliny11.9k
agents-cli
Command-line tool and skills to build and ship ADK agents to Google Cloud
Agent frameworks and tools Agent skills and plugins Developer tools
6.1k
A.I.G
AI red teaming platform for scanning agents, MCP servers, and model infra
Security testing and OSINT Agent frameworks and tools
6.9k
Agent Skills for Context Engineering
Skill pack teaching agents context and harness engineering patterns
Agent skills and plugins
Muratcan Koylan18.2k
Promptfoo
CLI for testing LLM prompts and red-teaming AI applications
Agent frameworks and tools Security testing and OSINT Developer tools
26.2k
Cua
Desktops, VMs, and drivers that let AI agents operate real computers
Agent frameworks and tools AI models and runtimes
30.4k
iFixAi
Command-line auditor that checks whether an AI agent does its intended job
Agent frameworks and tools Security testing and OSINT
30.5k
Heretic
Automatic abliteration tool that strips refusal behavior from LLMs
AI models and runtimes
Philipp Emanuel Weidmann36k
LightRAG
Graph-based retrieval-augmented generation library with a web UI
Agent frameworks and tools AI models and runtimes
40.2k