choncan
Follow
Stars
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Detection tools for the June 2026 atomic-lockfile AUR supply-chain attack. Consolidated from community Gists.
Track 20,710+ AI benchmark, eval, dataset, and data-quality records from 37 public sources, with linked evidence and daily updates.
A curated list of papers and resources on Recursive Self-Improvement (RSI) for AI.
Library for reducing tail latency in RAM reads
Kimi Code CLI — The Starting Point for Next-Gen Agents
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
The Little Book of Reinforcement Learning
A Survey on Ontology Engineering, Graph Engineering, Loop Engineering, Harness Engineering, Context Engineering and Prompt Engineering
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
BenchPress: calibrated LLM benchmark score completion
Let Skills Evolve Collectively with Agentic Evolver
LLMRouter: An Open-Source Library for LLM Routing
One sentence in, one draft paper out: spark-to-paper-skills automatically reviews papers, plans and runs experiments, and writes a research draft—typically using about $10 in API costs per paper.
Ouroboros — self-creating AI agent. Born Feb 16, 2026.
Generates original ARC-AGI-1-style tasks distribution-matched to the public eval set.
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fre…
An incremental parsing system for programming tools
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
The Open Cookbook for Top-Tier Code Large Language Model
Pragmata Pro doppelgänger made of Iosevka SS08
PragmataPro font is designed to help pros to work better