Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
12 repos
-
An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.
-
A Long-Horizon Benchmark for Self-Improving Inference Systems
-
MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents. Accepted at ICLR 2026; Best Paper Award at the NeurIPS 2025 MTI-LLM Workshop.
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
-
CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
-
FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
-
Measuring frontier coding agents on original, long-horizon engineering tasks
-
[ICML'26] Scaling Long-Horizon LLM Agent via Context-Folding
-
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
-
★ 7.4k zai-org/GLM-5GLM-5: From Vibe Coding to Agentic Engineering
-
🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness