Free to explore · curated by OneWave AI

Discover open-source AI tools.

1,004 apps, agents and plugins from GitHub, ranked on how actively they are maintained rather than on stars. Security review is in progress and every project shows exactly what has and has not been checked.

tech·an·dri·a/tɛkˈændriə/n.

A library for the tools of a new age. After the Library of Alexandria, which copied every scroll that reached its harbour before it went on the shelf.

Regular searchNames, topics, and keywords

/

AI searchDescribe a task, find the right tools

AI searches are sent to OpenAI.

ActivitySort

License detectedReviewed only (0)

Review is in progress. 1,004 projects are queued and none has been approved yet. Everything unreviewed is discovery metadata imported from GitHub — listed, not vetted.

Request a review · What we check

Ranked by total stars at the last daily refresh. This is not stars earned during the selected period. Star counts in the AI category are known to be inflated by fake-star campaigns, so activity and license are shown first.

5 projects matching “evaluation”Page 1 of 1

langfuse

langfuse/langfuse

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

Pushed yesterday.OtherTypeScriptAgents36.9k+365

WeKnora

Tencent/WeKnora

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Pushed yesterday.OtherGoPlugins36.4k+740

cua

trycua/cua

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

Pushed yesterday.MIT LicenseHTMLDeveloper tools31.7k+588

agent-starter-pack

GoogleCloudPlatform/agent-starter-packSlowing

Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.

Last push 4 months ago.Apache License 2.0PythonAgents6.6k+3

ouroboros

Q00/ouroboros

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

Pushed 2 days ago.MIT LicensePythonPlugins6.3k+25