Havuz

A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

A minimal modern terminal for AI coding experience — Sidebar workspaces; horizontal / vertical split panes; one-click agent launch; per-agen

~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown

让 AI 住在你 MacBook 的刘海里 · 零依赖开箱即用 · 多引擎并行的桌面 AI 伴侣（Swift 6 / SwiftUI / macOS 14+）

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

Plugin-first long-term memory for agent platforms — reference implementation of AMP (Agent Memory Protocol).

Open source AI company OS. 38 roles, 6 templates, 4-layer memory. Your AI company remembers everything — locally. npx clawcompany

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

Your First LLM-Wiki Conversation Knowledge Base

Harness-oriented agent system framework for production-grade LLM agent applications

The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs,

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

Turn Codex threads into an organization of long-lived domain agents.

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with

The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

The Vue framework for terminal UIs. SFC & JSX, Yoga flexbox, HMR, and testing out of the box.

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

LLM-ready reasoning surface over logs

Compose Skill (Compose Kit): agent skills for Jetpack Compose & Compose Multiplatform. Makes Claude Code, Codex, Cursor, Copilot, Gemini CLI

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite fi

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

An edge-native Multimodal Android Agent that integrates multimodal perception, memory and action

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

Tactical AI Workspace Monitor & EDR

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,

To know what models don't say out loud.

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

Transformer architecture explained step by step - the full architecture, every attention variant, positional embeddings, and every layer ins

Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.

Turn any document or a whole zip into an interactive knowledge graph, using a self-hosted Qwen3.6-35B-A3B-MTP on a single NVIDIA L4

AI Developer for Unreal Engine — An autonomous AI agent that creates Blueprints, C++, levels, materials, widgets, and more inside the UE5 ed

🌟 推理王国：关于 AI 推理机制的思想实验手册。从信息论、符号逻辑与表示学习出发，系统剖析大模型“智能”的本质。

Chiasmus is an MCP server that gives language models access to formal verification

Local-first code intelligence for AI assistants. Turns your codebase into a knowledge graph your AI can query, navigate, and remember. 25 MC

Free, local, open-source LLM cost analyzer - see where your LLM bill leaks, on your machine.

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacem

Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and Open

Antidote for fluffy specs, a toolkit for fact-driven development with AI agents

Hive compute for coding agent swarms - expand your personal compute by adding on-demand agentic swarms

A curated collection of AI learning materials

A pure-Python context management layer for LLM systems — retrieval, re-ranking, memory decay, and token-budget enforcement in one pipeline.

An LLM programming assistant engine built with Go, supporting WebSocket, multi-turn dialogues, tool calling, permission control, and skill e