browser-use/web-ui 16.6k
browser-use/browser-harness-js 494
browser-harness-js: a typed CDP bridge with no click() helper
BoxcarsAI/boxcars 463
Boxcars: A Ruby Tool-Orchestration Framework for LLM Applications
BigBodyCobain/Shadowbroker 11.4k +4 today
ShadowBroker: A Self-Hosted Map for Public OSINT Telemetry
baidu/vLLM-Kunlun 479 +1 today
vLLM-Kunlun: Running vLLM on Kunlun XPU Without Forking vLLM
baidu-baige/LoongForge 721
LoongForge: a multi-backend training framework for LLMs, VLMs, diffusion and embodied models
automataIA/graphrag-rs 529
graphrag-rs: A Rust GraphRAG Implementation With Three Deployment Paths
alexisfox7/PRO-LONG 459
PRO-LONG: an append-only session log plus a search skill for coding agents
alantech/marsha 466
Marsha: an LLM compiler that turns .mrsh specs into tested Python
aisa-group/PostTrainBench 581
PostTrainBench: A 10-Hour H100 Benchmark for CLI Agents Doing Post-Training
airbytehq/airbyte 22.3k +1 today
Airbyte: a 600-connector data movement platform with a split licence and a separate agent SDK
AI4Finance-Foundation/FinRobot 8,305 +11 today
FinRobot: A Multi-Agent Equity Research Platform Where the Numbers Come From Python, Not the LLM
0ca/BoxPwnr 467 +1 today
BoxPwnr: A Solver-Pluggable Harness for Grading Agents on CTF and Security Labs
Zyrexnn/Cybermes 973 +7 today
Cybermes: the manifest says 3.0.0 and the newest tag is v3.5.0
zh-plus/openlrc 684
OpenLRC pairs Whisper transcription with LLM translation, and hides its GUI
zeroc00I/DontFeedTheAI 669
DontFeedTheAI: the regex floor you can measure and the model floor you cannot
ymcui/Chinese-Mixtral 613
Chinese-Mixtral activates two of eight experts per token
Yeti-791/Tsec-Hackathon 854