Curated open source, analyzed
Find open source projects worth using
Hand-picked GitHub repositories with a clear analysis of what they do, who they are for and how they compare.
1,651 repositories ·170 topics· updated daily
Featured repository
skillrank: Find and Evaluate AI-Agent Skills
SkillRank is a Rust CLI for discovering, installing, and evaluating skills used by coding agents. Its paired local evaluations compare a skill-enabled run with a control to show changes in success, tokens, time, and cost.
Explore by topic
Jump into the most common areas across analyzed repositories.
Recently added
The newest projects added to the catalog.
skillrank: Find and Evaluate AI-Agent Skills
SkillRank is a Rust CLI for discovering, installing, and evaluating skills used by coding agents. Its paired local evaluations compare a skill-enabled run with a control to show changes in success, tokens, time, and cost.
agentevals: Evaluate AI Agents from OpenTelemetry Traces
agentevals scores AI agent behavior from existing OpenTelemetry traces, without rerunning agents or making extra model calls. It suits teams building instrumented agents that need local evaluation, golden-set checks, or CI quality gates.
ai-observer: Monitor AI Coding Assistant Usage Locally
AI Observer is a self-hosted OpenTelemetry backend and dashboard for tracking usage across local AI coding assistants. It brings token and cost data, traces, logs, and metrics together in DuckDB, with both OTLP ingestion and file-based import or watching for supported tools.
agent-observability: Monitor AI Coding Agents Locally
A self-hosted OpenTelemetry stack for monitoring Claude Code and OpenAI Codex. It routes telemetry to Prometheus, Loki, and Tempo, then presents usage, performance, and activity in Grafana dashboards.
web-design: Create Consistent Web Pages with a Claude Code Skill
web-design is a Claude Code skill that turns product briefs, reference URLs, or screenshots into an editable design specification before generating web code. It is suited to developers and designers who want a repeatable, spec-led workflow for building consistent pages.
oomwoo: Build a DIY Robot Vacuum
OOMWOO is a planned, hackable robot vacuum built around Raspberry Pi, ROS2 and 2D LiDAR. It is aimed at makers who want to build and customize a locally controlled vacuum, but its hardware and build instructions are still in development.
Leaderboard
Popular this week
The projects people found most through search, social and other sites over the last 7 days. Arrows show the move since last week.
Discover something different
A rotating sample from deeper in the archive.
aport-spec: Define Pre-Action Authorization for AI Agents
aport-spec defines the Open Agent Passport (OAP), a draft specification for verifying and authorizing AI agent actions before they occur. It is aimed at platform builders and developers implementing runtime policies, signed decisions, and interoperable agent credentials.
ggml: Build Portable Tensor Workloads for Machine Learning
ggml is a dependency-free C/C++ tensor library for building machine-learning workloads across CPUs and other backends. It is suited to developers who need low-level control over tensor operations, quantization, and deployment across different platforms.
shortest: Write End-to-End Tests in Natural Language
Shortest is a TypeScript end-to-end testing framework that turns natural-language instructions into browser tests, using Anthropic Claude and Playwright. It suits teams that want to describe user flows plainly while retaining hooks for custom assertions and setup.
Stay Updated
Get notified about new repositories and updates. Join our community of developers!