Skip to content
View SwiftieH's full-sized avatar
🏠
Working from home
🏠
Working from home

Organizations

@THUMNLab

Block or report SwiftieH

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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

Starred repositories

Showing results

A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, on-policy (OPD), cross-tokenizer, multimodal, and on-policy self-distillation.

Python 236 17 Updated Aug 13, 2026

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

C 66,292 4,187 Updated Aug 8, 2026

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

TypeScript 19,411 1,181 Updated Jul 16, 2026

A collective list of free APIs

Python 455,971 50,306 Updated Aug 13, 2026

Reference implementations of MLPerf® inference benchmarks

Python 1,616 646 Updated Aug 13, 2026

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

Python 1,093 73 Updated May 12, 2026
Python 685 69 Updated May 21, 2026

Stable Looped Models and their Scaling Laws

Python 174 12 Updated May 17, 2026

This is the official implementation of Tool Verification for Test-Time Reinforcement Learning. Code will be released soon.

1 Updated Mar 2, 2026

The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".

Python 184 14 Updated Feb 12, 2026

🔥 A collection of the Claude Code open source

TypeScript 2,797 2,450 Updated Apr 11, 2026

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Rust 195,074 109,169 Updated Aug 6, 2026

Claude Code plugins for development workflows

Shell 51 7 Updated Aug 13, 2026

Custom cache implementation to fix KV cache bug in ByteDance/Ouro-1.4B

Python 11 1 Updated Nov 12, 2025

τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Python 1,792 449 Updated Aug 12, 2026

An Open Foundation Model and Benchmark to Accelerate Generative Recommendation

Python 894 132 Updated May 18, 2026

The implementations of paper "Reinforced Preference Optimization for Recommendation" (ReRe).

Python 21 3 Updated Nov 16, 2025

WideSearch: Benchmarking Agentic Broad Info-Seeking

Python 151 18 Updated Oct 9, 2025

Marco Search Agent for Realistic and Challenging Agentic Search

Python 327 28 Updated Aug 9, 2026

Minimal reproduction of OneRec

Python 1,740 252 Updated May 14, 2026

Official Implementation of the paper "Jointly Reinforcing Diversity and Quality in Language Model Generations"

HTML 61 6 Updated May 8, 2026

[KDD2026] The repo contains the code for "FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets"

Python 240 24 Updated Feb 9, 2026
Python 277 42 Updated Oct 26, 2025
Python 1 Updated Sep 8, 2024

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Python 19,827 1,507 Updated Feb 27, 2026

Bridging LLM and Recommender System.

Jupyter Notebook 1,187 127 Updated Jan 27, 2026

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

Python 12,021 1,336 Updated Feb 5, 2026

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Python 74,146 12,013 Updated Aug 12, 2026
Next