Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.
Repository Index
78,850 visible repositories in the index
361–384 of 727 · Most stars
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
- evaluation
- evaluation-metrics
- guidebook
- large-language-models
automated censorship evasion for the client-side and server-side
- networking
- censorship-circumvention
- censorship-resistance
- geneva
Interactive evaluation for Neovim (Clojure, Fennel, Scheme, Python, JavaScript, PHP, R, Lua, Rust and more!)
- clojure
- clojurescript
- clojure-repl
- neovim
Open-Source Shellcode & PE Packer
- shellcode
- antivirus-evasion
- redteam
- hacktoberfest
A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.
- agent
- deer-flow
- develop
- electrobun
AI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.
- ai-alignment
- ai-governance
- ai-safety
- arxiv-papers
Avalanche: an End-to-End Library for Continual Learning based on PyTorch.
- continual-learning
- deep-learning
- pytorch
- lifelong-learning
This application gives Mac users in enterprise environments control over the administration of their machines by elevating their access level to administrator privileges on macOS. Users can set a timeframe in the application's settings to perform specific tasks, such as installing or uninstalling applications.
- open-source
- macos
- privileges
A Ruby gem for on-the-fly processing - suitable for image uploading in Rails, Sinatra and much more!
Benchmark datasets, data loaders, and evaluators for graph machine learning
- graph-machine-learning
- graph-neural-networks
- deep-learning
- datasets
SMBMap is a handy SMB enumeration tool
Rust library for single assignment cells and lazy statics without macros
- rust
- lazy-evaluation
Read your tfstate or HCL to generate a graph specific for each provider, showing only the resources that are most important/relevant.
- go
- terraform
- graph
- diagram
A proof-of-concept jupyter extension which converts english queries into relevant python code
- jupyter-notebook
- machine-learning
- python
Convenient unified display of the most relevant technical and tag data for video and audio files.
:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI
🤖 A Python library for learning and evaluating knowledge graph embeddings
- knowledge-graph-embeddings
- knowledge-graphs
- machine-learning
- link-prediction
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
- llm-guardrails
- llm-security
- llm-jailbreaks
- llm-scanner
Evaluation of Deep Learning Frameworks
[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"
AV/EDR evasion via direct system calls.
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
- deep-learning
- evaluation
- foundation-models
- instruction-following
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
- embeddings
- information-retrieval
- language-model
- text-classification