Havuz

Master LLM Fine-Tuning Trainer 2026: Advanced NLP Optimization Toolkit

Bilingual AI study coach that answers only from your own course material, with citations

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

A 21-day hands-on journey to mastering AI for DevOps — covering LLMs, GenAI, CI/CD, Kubernetes, cloud, automation, and AI-powered DevOps pro

Grimoire's Tome & The Grim Council. A Prompt Spellbook of /skills. The #1 Coding Wizard 🧙‍♂️📖

A zero-dependency Python tool to resolve relative Markdown links and inline images as Base64 strings for RAG and Multimodal LLMs.

MCP server that turns the pi coding agent into a steerable background worker: delegate a task, redirect it mid-run, and keep its context out

Your marketing department, automated. Open-source Grok Bot alternative specialized in marketing, distribution, and sales.

Скажи словами, что построить — получи работающую версию, проверенную до того, как её назовут готовой. Плагин для Claude Code: сам собирает т

轻量级 AI API 中转网关:统一管理多家上游 Key,提供 6 种负载均衡、失败自动切换、多维限流、响应缓存、额度监控与 Web 控制台。可在 Termux / Linux 直接运行,兼容 OpenAI 协议。

Spark-X2.5, yerel çalıştırma ve agent iş akışları için tasarlanmış 1.7B ve 4B boyutlarında açık dil modelleri serisidir.

Neden yükseliyor · Yeni model serisi; uzun context, küçük model boyutu ve agent/coding yeteneklerini aynı anda öne çıkarıyor. README'de 34 günlük yaş, 386 yıldız ve son 28 günde 9 commit ile 2 farklı yazar bilgisi var; bunlar erken ilgi ve güncel çalışma gösteriyor, ancak model performansını bağımsız olarak kanıtlamıyor.

A 14M-parameter LLM keeps a virtual fish tank alive on an $8 ESP32-S3 — distilled from a 26B teacher into 7.56 MB, no network.

Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model,

Open-source AI business orchestration platform for running governed AI agents across ERP, CRM, Microsoft 365 and other business systems.

🌊 34 free curated AI models (up to 1M context) for Oh My Pi & Pi. Thin by design — model list, relay proxy, tool-call diagnostics — add your

可扩展到各个领域的多 Agent 协作平台：自动分析任务，动态组建由不同角色组成的 AI 团队，协同完成复杂任务。

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk

The AI analyst that shows its work. Runs Python and R on your own machine, and traces every chart back to the code behind it.

Architectural linting for Swift developers and coding agents

Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix Halo

Local traffic visibility and privacy controls for coding agents. See what Claude Code, Codex and Copilot send to the model; mask secrets and

Mine GitHub issues for pain points — LLM semantic analysis, severity scoring, topic clustering & one-click market-research reports.

A visual UX configurator and scaffold generator for Agent frontends.

Gray is an open-source (MIT) AI agent harness shipped as one static Rust binary. Bash-only tools, resumable JSONL sessions, a self-compactin

Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

让 AI 帮你做缠论分析：自动画笔、线段、中枢，标出三类买卖点与背驰，每个信号都带失效价位。脚本负责计算，AI 负责讲人话；可复核、不荐股。适配 WorkBuddy / Claude Code / Codex / OpenClaw。Chan Theory (缠中说禅) engin

dst (data serve tool) — open-source semantic layer and MCP server between the AI your team uses and your data warehouse. Governed answers wi

A minimal workflow DAG (Directed Acyclic Graph) definition language and an asynchronous execution engine, implemented in Python.

browser-use, but for the entire desktop — give any AI Agent eyes and hands on Windows. MCP + SDK, VLM-optional, with visual loop, introspect

Open-source AI coding agent. CLI + Desktop app. Local (Ollama) and cloud (Claude/GPT) LLMs. Voice input. Privacy-first.

The Crusoe Developer Hub is the technical home for developers building AI applications and infrastructure on Crusoe Cloud. We publish three

5,200+ open-source icons for AI-era software — agents, MCP, RAG, LLMs — with an MCP server so your coding assistant picks real names. React,

Fine-tune the Qwen 2.5 AI model to act as a smart customer service assistant using Python and Unsloth on Google Colab.

Rome, kalıcı agent’lar, otomasyonlar ve uygulamalar oluşturup çalıştırmaya yönelik self-hosted bir platform sunuyor.

Neden yükseliyor · 35 günlük yaşında 553 yıldızın yanı sıra son 28 günde 223 commit ve 9 farklı yazar görünmesi, erken dönem ilgisine ve kayda değer geliştirme hareketliliğine işaret ediyor; bunlar tek başına kullanım veya ürün olgunluğu kanıtı değil.

Time-shifting task delegation for DeepSeek Harness (dsh): plan tasks at leisure, they run unattended off-peak, come back to a report. Human-

带 AI 精读大型开源仓库的方法论：四阶段流程、可复用模板、28 条踩坑清单，核心是让每个技术论断都可回溯到源码具体行

Console is a private, native Android app for your self-hosted Hermes Agent: chat that shows the agent's work, voice, bots and rooms, cron, t

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

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

One Hermes conductor. Many coding CLIs. Zero trust in self-reports. Production multi-harness orchestration patterns: worktree lanes, verific

Run several Claude Desktop accounts side by side on macOS, sharing Claude Code chats between them

A minimal local coding agent built on the CloudWeGo eino framework — the framework-variant sibling of mini-coding-agent-go.

AI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NP

A repo investigator for Claude Code and Codex. Offload codebase investigation and get up to 2.7× as much work from the same limits.

The same HTTP API in 10 languages at 3 sizes, 30 implementations. Token cost for LLM agents, plus cold start, latency, throughput, CPU and m

以斯坦福公开课 CS 336 为基底，零基础手搓大模型

Compile your own LLM for the Hailo-10H — an open pipeline from Hugging Face checkpoint to a self-contained HEF, served with hailo-ollama.

Run a team of AI agents on your own computer. Your files, browser sessions and passwords stay local. Works with Claude Code, Codex, hosted o