新秀榜（30天）

AI-native office suite (Docs, Sheets, Slides, PDF) where the Hermes Agent is the brain — open standards, byte-preserving round-trip, 100% local.

Lightning-fast, free, local first voice dictation for macOS with on-device transcription

A memory plugin for AI coding that turns engineering experience, repository knowledge, and your way of working into memory that remains useful in future tasks.

An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.

Codex skill for turning everyday photos into poetic white-paper hand-drawn illustrations.

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

A long-horizon benchmark harness: give a coding agent a real game engine, professional conditions and time, and ask it to build an open-world game. Harness only, no results.

Free, open source voice dictation for macOS. On-device transcription with Apple's Speech framework. No cloud/no API keys/no account.

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.

4DAnyone: Create Anyone in 4D from a Casual Monocular Video

HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.

Agent Skill for turning Chinese classical poems into vertical Chinese-art videos with ImageGen stills, Docker I2V, calligraphy captions, retained ambience, BGM and final MP4 QA.

Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.

Boot your PC straight into an LLM. Rust, UEFI-resident, no operating system underneath.

尚硅谷 AI 课程笔记

🪐 HelixWorld: real-time interactive audio-visual world model.

25 fixed illustration styles for Codex: 9 skills, prompt recipes, and visual references

让 Codex 根据最终结果生成标题、注释、commit 和 PR，减少被否决方案在交付中的残留。

Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.

Pi extension: rewrite rough prompts into precise technical prompts before send