-
sglang Public
Forked from sgl-project/sglangSGLang is a high-performance serving framework for large language models and multimodal models.
Python Apache License 2.0 UpdatedApr 29, 2026 -
synthetic-pretrain Public
Code release for a small-scale adaptation of self-improving pretraining, interleaved thinking SFT, RLMT, and causal thought-use probes on Qwen3-0.6B.
Python Other UpdatedApr 28, 2026 -
metacognition Public
Measuring whether language models know when to change their mind. d-prime for belief revision across Qwen3.5 0.8B-9B.
Python UpdatedApr 20, 2026 -
autoagent Public
Forked from kevinrgu/autoagentautonomous harness engineering
Python UpdatedApr 3, 2026 -
surprisal Public
Open-ended scientific discovery via Bayesian surprise. MCTS + Claude/Codex agents + Docker sandboxes.
-
ai-scientist-training Public
Synthetic Prime/verifiers environment for epistemic experiment selection and belief revision
Python UpdatedMar 22, 2026 -
cohere-aya-analysis Public
Mechanistic interpretability analysis of Cohere Aya Expanse 8B
-
test-time-training Public
Code for "Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation"
-
opensec-env Public
Dual-control RL environment for incident response training with adversarial evidence, OpenEnv-compatible, plus evaluation tooling and datasets.
-
Slime-RLVE Public
Verifiable math/logic environments for slime RL training
-
Tau2-RL-Pipeline Public
Multi-turn tool-use training pipeline for tau2-bench using slime
-
slime Public
Forked from THUDM/slimeslime is an LLM post-training framework for RL Scaling.
-
-
verl Public
Forked from verl-project/verlverl: Volcano Engine Reinforcement Learning for LLMs
-
verifiers Public
Forked from PrimeIntellect-ai/verifiersVerifiers for LLM Reinforcement Learning
Python MIT License UpdatedJul 16, 2025 -
mlx-lm-lora Public
Forked from Goekdeniz-Guelmez/mlx-lm-loraTrain Large Language Models on MLX.
Python Apache License 2.0 UpdatedJul 7, 2025 -
acp-evals Public
ACP Evals is an evaluation framework for multi-agent systems built on the Agent Communication Protocol.
-
ambient Public
[Open AI Hackathon] A meta-agent wellness platform that auto-generates personalized AI agents in one click
-
atropos Public
Forked from NousResearch/atroposAtropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
-
github-webhook-analyzer Public
A multi-agent system that automatically analyzes GitHub repository events (PRs, Issues, Comments) using Orchestra's AI framework.
Python UpdatedMar 29, 2025 -
deephermes-mlx Public
A Python implementation for DeepHermes models on Apple Silicon
-
cortex-1 Public
NEAR Cortex-1 is a specialized AI model that can reason, understand, and predict crypto market movements by learning from cross-chain data.
-
shade-agent-template Public
Forked from NearDeFi/shade-agent-twitterJavaScript Other UpdatedMar 2, 2025 -
-
near-intents-example Public
Forked from referencedev/test-intent -
deepseek-r1-finetune Public
A step by step guide to fine-tuning the DeepSeek R1 Distilled models on Apple Silicon machines.
-
Agent-R Public
Forked from ByteDance-Seed/Agent-RResources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"
Python Apache License 2.0 UpdatedJan 25, 2025 -
mflux Public
Forked from filipstrand/mfluxA MLX port of FLUX based on the Huggingface Diffusers implementation.
Python MIT License UpdatedJan 5, 2025 -
HunyuanVideo_MLX Public
Forked from gaurav-nelson/HunyuanVideo_MLXHunyuanVideo ported to run on Native Apple Hardware (requires M1 or better CPU)
Python Other UpdatedJan 5, 2025 -
mlx-omni-server Public
Forked from madroidmaq/mlx-omni-serverMLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seaml…
Python UpdatedJan 5, 2025
{{ message }}