Awesome

GitHub projects from awesome lists

Search awesome repositories

Search names, descriptions, topics, tags, and stacks, then tune results by ecosystem, freshness, health, and cross-list signal.

Continue with GitHub Browse awesome lists Request a list

Repos indexed: 21,464
Awesome lists tracked: 149
Current results: 2

Find repositories

Start broad, then narrow by ecosystem, freshness, health, and growth.

Unsure which signals matter? Read the repository shortlisting guide.

Clear 1 refinement

Search repositories

Search mode

Keyword Semantic

Tune results

The controls most people need first.

Awesome list

Language

Freshness

Sort

Direction

More filters Topics, generated tags, stack, files, age, archive status, and growth.

Ecosystem

GitHub topic

Generated tag

Framework or stack

Package manager

Files

Has file

Choose a suggestion or use commas to require multiple files.

Health

Minimum stars

Repository age

Uses known first-commit dates.

Archive status

AI development signals

Momentum

Unmaintained for

Commit velocity

Star growth

Reset filters

2 repos shown

Topic: agent-reliability

Browse

Highlighted

Open highlighted repo slot

Put your repository first

Promote a GitHub repo at the top of Awesome repository list views for 7 days.

FailproofAI/failproofai

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.

AI dev

Stack

MDX Next.js pytest React Tailwind CSS Bun Cargo npm

GitHub topics

#agent-failure #agent-harness #agent-observability #agent-reliability #agent-tracing #ai-agent

Updated: 2026-09-17
Lists: 1 list mention
First commit: 2026-04-06
History: 1 history point
License: NOASSERTION
Issues: 36 open

4,922

stars

Forks: 492
Commits: 649 commits
Star growth, last 7 days: No 7-day history
Commit velocity, last 7 days: No 7-day history

Website GitHub

ProvablyAI/sourcerykit

Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstream agents detect 100% of errors and retry to achieve a 50% jump in answer accuracy.