Skip to content
View JarvisPei's full-sized avatar

Block or report JarvisPei

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Reverse engineer anything with agents, from app behavior down to native binaries.

TypeScript 466,104 114,061 Updated Nov 17, 2026

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

Python 1,707 25 Updated Sep 26, 2026

A curated list of research on Recursive Self-Improvement (RSI): AI systems that improve their own weights, prompts, memory, skills, tools, workflows, source code, or improvement mechanism.

JavaScript 4 2 Updated Aug 13, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 282,950 35,069 Updated Nov 17, 2026

Democratizing Reinforcement Learning for LLMs

Python 5,923 644 Updated Oct 16, 2026

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

Python 461 54 Updated Aug 30, 2026

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

Python 523 45 Updated Jan 28, 2026

WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.

Python 659 47 Updated Mar 3, 2026

分享AI Infra知识&代码练习:PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

Jupyter Notebook 4,390 435 Updated Sep 20, 2026

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

Python 7,158 595 Updated Nov 17, 2026

Elevate your AI research writing, no more tedious polishing ✨

35,970 2,535 Updated Aug 19, 2026

Academic Research Skills for Claude Code: research → write → review → revise → finalize

Python 57,311 4,359 Updated Nov 17, 2026

Open-source harness distillation: frontier teachers improve prompts, tools, validators, skills, and runtime policies around weaker models.

Python 1 Updated Jul 7, 2026

将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿,你的 AI 科研副导师。

Python 12,796 759 Updated Nov 5, 2026

OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. …

Python 1,775 223 Updated May 7, 2024

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Python 13,078 1,425 Updated Oct 17, 2026

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

Python 5,771 493 Updated May 21, 2025

Train transformer language models with reinforcement learning.

Python 19,754 3,152 Updated Nov 17, 2026

Headless Slay the Spire 2 CLI — play the full game from a terminal.

C# 285 68 Updated Oct 29, 2026

DFlash: Block Diffusion for Flash Speculative Decoding

Python 6,245 445 Updated Aug 18, 2026

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

Python 9,702 1,329 Updated Nov 16, 2026
Jupyter Notebook 416 38 Updated Sep 17, 2025

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

Python 664 58 Updated Jun 12, 2026

Make your OpenClaw agent self-improving

TypeScript 10 Updated Mar 31, 2026

The implementation for the paper, FuseGPT: Learnable Layers Fusion of Generative Pre-trained Transformers.

Python 5 1 Updated Jan 15, 2025

[ACL 2026 Main] Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis

Python 55 13 Updated Jun 30, 2026

[COLM 2026] Proactive Inference for Efficient Mixture-of-Experts

Python 10 Updated Jul 23, 2026

SCOPE: Self-evolving Context Optimization via Prompt Evolution - A framework for automatic prompt optimization

Python 83 7 Updated Mar 26, 2026
Next