The best-benchmarked open-source AI memory system. And it's free.
Repository Index
57,138 visible repositories in the index
1–24 of 80 · Most stars
OpenMMLab Detection Toolbox and Benchmark
- object-detection
- instance-segmentation
- fast-rcnn
- faster-rcnn
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Write scalable load tests in plain Python 🚗💨
- locust
- python
- load-testing
- performance-testing
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.
- ai-agents
- android
- test-automation
This repo hosts Prowler OSS (CLI and Local Server). Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment for Humans and AI Agents.
- security
- security-tools
- security-audit
- security-hardening
A MNIST-like fashion product database. Benchmark :point_down:
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.
- outlier-detection
- anomaly-detection
- outlier-ensembles
- machine-learning
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
- semantic-segmentation
- pytorch
- pspnet
- deeplabv3
OpenMMLab Pose Estimation Toolbox and Benchmark.
- pose-estimation
- human-pose
- pytorch
- hrnet
TranslatedNational Smart Education Platform for Primary and Secondary Schools e-textbook download tool, which helps you get the PDF file URLs of e-textbooks from the Smart Education Platform and download them, making it more convenient for you to get textbook content.
- python
Insular email distribution - mail server as Docker images
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
- evaluation
- benchmark
- large-language-model
- llm
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
- localllm
SWE-bench: Can Language Models Resolve Real-world Github Issues?
- benchmark
- language-model
- software-engineering
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
Benchmarks of approximate nearest neighbor libraries in Python
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
- action-recognition
- temporal-action-localization
- pytorch
- video-understanding
IntelOwl: manage your Threat Intelligence at scale
- security-tools
- python
- threat-intelligence
- ioc
Python package for the evaluation of odometry and SLAM
- slam
- odometry
- evaluation
- metrics
One 8 KB skill that replaces REA (Reverse Engineer Anything): plain CLI tools, no MCP. Benchmarked: 38% faster, 35% cheaper.
[NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
- data-mixture
- data-science
- data-selection
- data-reweighting