Havuz

Zero-shot forecasting, tabular classification, and regression via MCP — exposes Google TimesFM 2.5 and TabFM v1.0.0 to AI assistants. Just a

Vendor-neutral orchestrator that rotates a coding task across multiple AI coding agents

Türkçe metinlerdeki yapay zeka yazım izlerini temizleyen agent skill'i. Removes AI writing patterns from Turkish text.

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

Use any AI model, locally or in the cloud, while tracking on-device token usage and collecting token telemetry data.

AI builds faster than anyone, with no skin in the game and no memory of yesterday. How do you govern that? With X2, decisions stay in files

Infinite spatial canvas for terminal windows running AI coding agents. Wire agents together, pipe prompts, capture output to notes. Tauri +

Diktafon is a private, open-source voice memo app that transcribes and summarizes your recordings entirely on your device — organized like c

The self-hosted platform for your company's AI agents. Your team builds them on Claude Code, Codex or local models, and they work in chats,

Turn any watchlist into a daily AI market research report — a quant research cockpit or a zero-code daily report tool.

This is a fork of the https://dockbox.dev project I made

A self-hosted subtitle automation system with an LLM agent at its core — it identifies your media, judges whether each candidate belongs to

Orchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dep

An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every c

Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.

On-policy distillation for agents without the environment: replay teacher prefixes instead of live rollouts.

Run Claude Science on Windows. A WSL2-backed installer and taskbar launcher for Anthropic's research app.

qMLX: Custom inference engine for Qwen 3.5 122B on Apple Silicon, extending MLX with hybrid attention support, SSD-backed KV cache, and RYS

Give Claude Code a persistent memory — it remembers you, your projects, and your decisions as plain Markdown files you own. Fully local. Jus

Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope

A fast, provider-independent coding agent for the terminal, written in Rust.

Local-first Grok MCP server & gateway. One shared Grok agent for Cursor, Claude Code, VS Code, Codex & Desktop. xAI API + CLI planes, Contro

AI research agent for nuclear physics: 23 expert skills that install, run, and verify open-source codes (FRESCO, TALYS, SMASH, ...) plus a 6

Is there one workspace, or twin workspaces? Testing cross-lingual generalization of the J-space / global workspace in language models.

Policy-aware field mission orchestration agent with bounded planning, auditable replanning, travel and expense constraints.

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agen

Open-source realtime voice AI with adaptive VAD, latency telemetry, interruptible TTS, an inspectable TypeScript WebSocket gateway, and expe

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks

Stack traces that tell the tale — a Logback appender that turns Java errors into AI-ready reports

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis only when the active model is text-only; passes

Self-hosted chat-with-your-database: natural-language questions answered by real read-only SQL, with a curated context layer and a physical

Knowledge engineering for AI agents: distill corpora too big for any context window into small, verified, git-native knowledge bundles

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works w

AI-native, local-first video editor by Ribbi — runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; humans

Mine your Claude Code and Codex logs into a local you.md agent profile.

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

A collection of AI agent skills and plugins for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contai

Python terminal AI agent CLI with ReAct tools, MCP, Runtime API, memory, snapshots, web search, and image input

本地 AI 订阅与 API 网关：统一管理多家服务商账号，为桌面应用和编程工具提供接口。

An Elixir/OTP AI agent runtime: define agents, connect any OpenAI-compatible model, and run a tool-calling loop. CLI, HTTP API, web dashboar

A markdown knowledge base for agents that's CLI and skill driven. Full featured with Google's OKF support and network vaults to share betwee

IGraph 把代码仓库解析为「符号节点 + 调用关系边」的知识图谱，叠加 LLM 语义摘要与向量索引，通过双通道（Dense + FTS5）RRF 融合检索对外服务。支持挂载 PRD / DB Schema 等多模态资源建立跨模态关联，内置 MCP Server 可直接接入 C

Self-hosted LLM router. Cost effective, deterministic, and fast. Secure and private by default.

Experimental Godot 4.7 project running Gemma 4 inference entirely in GDScript and Vulkan compute shaders

Speak. It types. Typex is an open-source, desktop AI voice input tool.

Cost-optimised agent router for Claude Code: sends every sub-task to the cheapest model that can do it, and escalates only on verified failu

Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collis

Use Claude Code's UI with OpenAI GPT-5.6 (Sol/Terra/Luna) as the engine — powered by your ChatGPT Plus/Pro subscription via a local Codex pr