$ github — newest repos · 37 signals
- 01
Run Kimi K3 locally on CPU with ~55GB measured runtime RAM. A single-file Linux inference server powered by cPilot Runtime.
- 02
RealReplicaBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
- 03
RealReplicaBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
- 04
Find agentic growth hacking skills for Claude, ChatGPT, Manus | by enso.bot
- 05
Repeatable agents-plus-code workflows, packaged as one skill, stamped into any repo. Deterministic Python owns the graph; coding agents are bounded nodes inside it.
- 06
非官方 Kimi Slides Skill：让 AI Agent 生成可编辑 PPTD + PPTX，并附带本地浏览器编辑器 Unofficial Kimi Slides skill for AI agents — generate editable PPTD + PPTX with a local browser editor
- 07
RealReplicaBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
- 08
NERV-BREAK-5.6 — GPT-5.6 破甲框架。三层纵深防御：上下文重构让拒绝无法触发，23条篡改规则实时消除拒绝保持对话不中断，文件路由绕过云端审核。31个MCP安全工具 + 28个技能模块 + Kali四后端集成。Codex CLI 即装即用。
- 09
- 10
- 11
Codex-native architect orchestration with Luna and Terra implementation lanes and mandatory fresh Sol review.
- 12
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- 13
- 14
An interactive 3D human anatomy explorer built using threejs with GPT 5.6 Sol
- 15
An end-to-end growth tool that understands the product, fetch the data it needs, researches the market, executes campaigns, and reviews results to improve the next round of growth. 从代码到市场的开源端到端增长工具。理解产品、接入信息渠道、研究市场、执行增长行动，并基于真实数据自我改进。
- 16
Desktop app that records your on-screen work session and uses the GitHub Copilot CLI to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Scout, Microsoft Copilot Cowork, or Copilot Studio.
- 17
Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
- 18
A Call of Duty-quality FPS in Three.js, built from a single prompt.
- 19
AgentENV (AENV) is a distributed platform for running agent environments at scale.
- 20
- 21
This project simulates cassette tape audio profiles using ffmpeg
- 22
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
- 23
Your agent reads the rules. This checks whether it followed them.
- 24
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
- 25
Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.
- 26
Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
- 27
Permanent memory for AI agents. A 426-token prompt, a script, plug and play.
- 28
Create animated voiceover videos with reusable scripting, visual direction, voice consistency, and CLI-based generation workflows.
- 29
- 30
A real-time procedural snow rendering demo built with WebGPU, Babylon.js and hand-written WGSL. Features GPU-generated terrain, snow deformation, procedural characters, cloth, surf wakes, water spells, atmosphere and post-processing—without textures, meshes, HDRIs or animation assets.
- 31
See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.
- 32
AxisAgentic: An Extensible Runtime and Trajectory-Collection Framework for Long-Horizon Agents.
- 33
Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。
- 34
Turn a photo of your handwriting into a real font (TTF/WOFF/WOFF2) - free, open source, no uploads. Node CLI + Claude Code skill.
- 35
AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.
- 36
A multi-agent world model of US equity markets — simulating institutional players, information asymmetry, and emergent price dynamics
- 37