Havuz

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augment

Self-hosted decision model (selfjev-4b) with a Jev-compatible API: Python SDK, server, fine-tuning and RLCD.

Home Assistant app: an LLM fallback for Assist that learns from what Assist couldn't handle and suggests aliases, automations and scenes

An experiment-driven LLM engineering lab with 9 reproducible Python experiments exploring token economics, API costs, caching, context growt

闲亭 DeskPark — 简洁优雅的网页桌游平台：斗地主、掼蛋、德州扑克、四川麻将；单人人机与多人联机、房间聊天、像素虚拟形象、AI 托管人机，Docker 一键部署

Memory for coding agents that checks itself against your code. Every memory carries evidence; stale facts never reach the context.

本地运行的 AI 互动小说运行时。导入作品、连接模型，在浏览器中阅读、选择行动或自由输入；支持记忆、状态、分支与作品创作。

aisync — AGENTS.md, but for live coordination between AI tools. One standup for all your AI coding tools: shared rules, a hash-chained journ

A 4B decision model built for Korean.

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl-

说一句，界面在画布上长出来 · https://wuch-ai.net

Open-source alternative of Whisper flow. BYOK

Comprehensive scholarly work with your Zotero library: database search, screening, cited answers and checked literature reviews (formerly Zo

Make AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and

An experiment-driven laboratory for understanding LLM sampling strategies. Explore how Temperature, Top-k, and Top-p influence token probabi

给任意 LLM API 补上工具调用能力的纯 Go 中间件库。

The Virtual Filesystem Interface for AI Agents

AIが書いた日本語を、意味を変えずに読みやすく整える、指示欄に貼る400〜500字の指示文

Local, provider-agnostic agentic hub: an orchestrator and a squad of little monsters on your machine

A virtual agentic office in 3D where four AI robot agents (Evan, Lummi, Athena, Zed) chat, collaborate and get work done. Zed, the reception

DeepSeek Harness 官方通道破甲预设 · complete:true 整段替换 · 自带工具说明书 · 不改宿主 · 升级不丢

Run stock llama.cpp with the stock Unsloth Qwen3.6-35B-A3B 4-bit on a 16 GB Mac.

A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.

Official repository for MemT-1.0

Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call

Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md

Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works

qwen2API çok dilli (i18n) fork'u • Multi-language (i18n) fork of qwen2API — WebUI artık Çince, İngilizce ve Türkçe / UI now in Chinese, Engl

Hermes Bot — a native Mac interface to the Hermes agents you already have.

Agent dashboard runs reliability scans, skills, and network access probes.

ARTEX ：AI 自主渗透测试系统（Go + Next.js），基于 Autumn-27/ARTEX v0.3.15（e6ec569，AGPL-3.0）。原版 v0.3.15 下载说明与恢复指引见 README。

A local AI agent built from scratch in Python with Ollama: conversation memory, system prompts, and multi-step tool calling.

自托管的 Telegram → 115 网盘自动转存：AI 识别分享链接，审批后转存并按 Jellyfin/Emby 规范整理入库

AGENTS.md contract for AI coding agents + zero-dependency linter + SessionStart hook. Works with Claude Code, Codex, Cursor, Copilot.

📚 An educational, step-by-step implementation of LLM KV cache reuse — learn prefix caching, chunk keys, storage & eviction, from pure Python

风插 2.0 — DSH 推理语域锚定预设：两个 agent preset（风插标准/风插 PTC）在 runtime-context 快照头尾各注入一次形式化约束，使推理以第一人称复数展开。定性=硬指令约束（非吸引子）；未证明能力提升，未证明无负面作用。Apache-2.0

A skill for AI coding Agents; Free OEM service manuals -> procedure, torque table, labelled figures. 69 makes, 1960-2025. Agent skill + stdl

Windows utility focused on ollama model manager, model library, and download local models for local AI workflows.

Windows utility focused on model download manager, resumable downloads, and local model queue for local AI workflows.

Windows utility focused on one-click local AI setup, local AI runtime, and Windows AI setup for local AI workflows.

Windows utility focused on cuda setup, nvidia local AI, and cuda environment for local AI workflows.

Windows utility focused on out of memory recovery, vram error, and local AI crash for local AI workflows.

A moddable training framework for pre-training ablations.

Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, ll

Edge-cloud vision reference: TFLite gate, MQTT, LLM fallback, temporal memory, calibrated metrology, and a beginner ESP32/serial kit

Windows utility focused on model storage cleanup, unused local models, and AI cache cleanup for local AI workflows.

All-In 播客中文版：全部单集的官方音频、视频、文稿与 AI 中文精读 | Chinese companion site for the All-In Podcast

Native Android client for OpenCode Go. Chat with GLM, Kimi, DeepSeek, Qwen and more, with streaming Markdown, web search, thinking effort an

A local privacy firewall for AI agents: masks secrets and personal data before a request leaves your machine and restores them in the answer

DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-