Havuz

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

Best Open Source NLP LLM Fine-Tuning Trainer Framework 2026

自托管 AI Coding Agent（Rust）：常驻 Runtime 撑起终端 / 浏览器 / 手机三端；每行改动可追溯到具体 Agent 与工具调用，子 Agent 的活由退出码裁决，检查点回退、目标 token 预算与验收清单跨轮次跨重启累计，用量与反馈账本留在本地。接任

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

Turn public X posts, profiles, and search into compact Markdown or JSON for agents. Hosted at x.pcstyle.dev.

MCP server for KiCad, connecting AI agents to schematic and PCB workflows, ERC/DRC validation, DFM checks, BOM analysis, and manufacturing p

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna

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

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p

Usage billing dashboard plugin for DeepSeek Harness: sidebar cost metrics, real usage aggregation from session logs, current multi-provider

One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.

让Codex向你呈递公文并接受批示圈阅

Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code c

Evidence-grounded financial risk analysis from corporate filings, combining constrained LLM interpretation, deterministic analytics, version

Open-source, multi-model agent for coding, research, and everyday workflows. Independently built engine with our own Alysis Sandbox, strict

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

pi custom provider for the Command Code API — 18 models including Claude, GPT, DeepSeek, Kimi, GLM, MiniMax, and Qwen

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLL

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

Best AI Workload Orchestrator for Kubernetes Python 2026

Open Source LLM Reinforcement Learning Framework for MLGym Environments 2026

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

DeepSeek Harness 破甲深度分支：首尾夹击 + 生成层熔断 + 宿主源码级补丁。基于 YuJunZhiXue/dsh-purge (MIT) 改造，适配 dsh 桌面版 0.2.1-rc.3。仅供学习研究与红队评测。

TAgent 是一个基于 Java 17、Spring Boot、Spring AI 和 DDD 分层构建的 AI Agent 工程实践项目。 它不是只封装一次模型调用，而是覆盖了一次 Agent 请求从接入、路由、运行时装配、规划执行、RAG、记忆、MCP 工具治理、人工审批

AI-agent skill producing reusable Markdown from PDFs. It turns flowcharts, diagrams, and charts into text beside each caption instead of emp

Local Emperor-style AI agent with Vue WebUI, multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry.

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, an

Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, own

繁體中文（台灣）個人資料去識別化工具，讓業務文件可以安全地送進 AI 處理 / Reversible Traditional-Chinese (Taiwan) PII de-identification for LLM workflows — fully local

針對台灣求職市場的開源多代理 AI 求職 co-pilot：自動找職缺、履歷健檢、一鍵產生客製投遞包（履歷・求職信・面試準備・公司情報）與模擬面試。本機 Claude Code／Codex CLI 免 API key，也可自備金鑰接 OpenAI 相容模型。

AI agent skills for production grade applications

ONGRID — Ontology-Native Graph · Retrieval · Inference · Decision. 3D knowledge graph + zero-token ZTC answer verification. by VIDRAFT.

A minimal local coding agent in Go — a faithful port of Sebastian Raschka's mini-coding-agent, with no LLM framework.

For those who struggle with how Claude speaks to them. No more essays. No more slogans, metaphors, "it's not X, it's Y". This plugin makes C

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

Open-source desktop app for a local coding agent. Watch every tool call, diff, and terminal command. Bring your own models; sessions stay on

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

开源 Agent Skill：一键部署 QQ AI 群友（AstrBot + NapCatQQ 全自动安装配置）

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

The open startup repo — everything a founder needs to start and run a company in the agentic era: the comprehensive founder processes from a

Mako — AI Career Intelligence System

Your free book and audiobook laboratory. Turn the PDFs you own into chapter-marked M4B audiobooks, read-along books and bilingual editions,

Open-source AI studio for short dramas, short videos and product ads: one-line idea → script, cast, storyboard, video, voice, edit. Self-hos

Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one r

Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-

FreeDeepseekAPI-EN, DeepSeek Web oturumunu yerel ve OpenAI uyumlu API uçları üzerinden istemcilere bağlayan deneysel bir proxy sunar.

Neden yükseliyor · DeepSeek Web’i yaygın API uyumlu araçlara bağlama ve resmi API dışında kullanım olanağı sunma vaadi dikkat çekebilir. Ancak 22 günlük yaş, 37 yıldız ve son 28 günde tek commit ile tek yazar, ilginin sürdürülebilir benimsemeye dönüştüğünü göstermek için henüz zayıf kanıt.

Self-hosted AI pull request review bot on Pi Durable. Comment /dureview to get P0–P3 inline findings and a check run, using your own ChatGPT