remotion-dev/remotion
docker-desktop-windows/docker-desktop
stablyai/orca
cslol-manager/ltk-manager
thedotmack/claude-mem Collection
Agent Harness
The Agent Harness collection tracks 12 curated open-source projects, 12 of them live on TrendingRepo right now — ranked by a cross-source momentum score blending GitHub star velocity with mentions on Hacker News, X, Bluesky, Product Hunt and Dev.to.
Live · top 12 repos · sorted by momentum across 24H
LIVE · 37m| # | Repository | Stars | 24h | 7d | 30d | Trend | Mentions | Actions |
|---|---|---|---|---|---|---|---|---|
| 01 |  agno-agi/agno Build, run, and manage agent platforms. | 41.4K | +2+0.0% | +133+0.3% | +513+1.3% |   live on X / Twitter | ||
| 02 |  pipecat-ai/pipecat Open Source framework for voice and multimodal conversational AI | 13.7K | +4+0.0% | +141+1.0% | +683+5.2% | live on X / Twitter | ||
| 03 |  crewAIInc/crewAI Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. | 56.2K | — | +328+0.6% | +1.8K+3.2% |   live on X / Twitter | ||
| 04 |  letta-ai/letta Platform for stateful agents: AI with advanced memory that can learn and self-improve over time. | 24K | +10+0.0% | +85+0.4% | +452+1.9% | live on X / Twitter | ||
| 05 |  SWE-agent/SWE-agent SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024] | 19.9K | +2+0.0% | +53+0.3% | +291+1.5% | live on X / Twitter | ||
| 06 |  microsoft/promptflow Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring. | 11.2K | +1+0.0% | +7+0.1% | +33+0.3% | | ||
| 07 | microsoft/autogen A programming framework for agentic AI | 60K | +2+0.0% | +151+0.3% | +772+1.3% | live on X / Twitter | ||
| 08 |  AgentOps-AI/agentops 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 | 5.7K | — | +13+0.2% | +83+1.5% | live on X / Twitter | ||
| 09 |  openai/evals Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks. | 19K | +1+0.0% | +64+0.3% | +250+1.3% | live on Dev.to | ||
| 10 |  THUDM/AgentBench A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24) | 3.6K | +2+0.1% | +22+0.6% | +85+2.4% | | ||
| 11 | microsoft/TaskWeaver The first "code-first" agent framework for seamlessly planning and executing data analytics tasks. | 6.2K | — | +3+0.0% | +15+0.2% | | ||
| 12 |  run-llama/llama_deploy Deploy your agentic worfklows to production | 2.1K | — | -1-0.0% | -1-0.0% | |