Havuz

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt

Web UI & dashboard for Hermes Agent — chat, memory, skills, terminal, approvals, multi-agent orchestration. Self-hosted.

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine

HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.

RAG ReAct Agent - A Retrieval-Augmented Generation system with ReAct (Reasoning+Acting) agent loop for intelligent question answering with m

Token telemetry dashboard for AI autonomous and coding agents — tracks tokens, sessions, tool calls & reasoning across Hermes agent, Claude

distill any book down to its spine

Deterministic textlint rules and CLI for catching prose slop in English Markdown.

基于 RAG（免微调）从聊天记录唤起语气与回忆：让曾经对话的温度，延续为往后的陪伴。 | Zero-finetuning RAG to revive tone and memories from chat logs: Let the warmth of past conversa

An end-to-end framework for multi-speaker transcription that jointly models who spoke, when, and what.

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

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

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses).

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

Your AI intranet: network the computers you already own for inference and training.

An esoteric programming language built to break LLMs and coding agents.

Anyone can predict the future. Almost nobody keeps the receipt. A hash-chained prediction ledger for LLMs — sealed before the answer exists,

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

Private AI on premise

Lightweight, stateless privacy gateway for LLM APIs — redact secrets before OpenAI/Anthropic upstreams and restore them transparently in SSE

LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented an

Research artifacts from Hyra (/ˈhaɪ.rɑː/)

Free, open-source AI video editor for macOS, Windows and Linux — drive the whole timeline from any MCP client.

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

Servidor MCP fiscal brasileiro: CNPJ, NF-e, NFS-e, CT-e, SPED, eSocial, Simples Nacional, Reforma 2026. 44 tools, zero-cadastro, tabelas off

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

Apexo: An open-source, general-purpose coding agent for terminal (TUI), web, and desktop with autonomous goals, workflows, persistent memory

11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from

An open-source inference engine for AI functions in SQL

Self-hosted AI roleplay chat platform you run on your PC or personal server, forked from Risuai

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that runs entirely on your own provider API keys (BYOK). Bring you

Full-market stock discovery for AI agents: A-shares plus US/HK/JP/KR/TW/IN, auditable YAML strategies, optional LLM ranking, sector-diversif

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Windows 微信 4.1.12+ 聊天记录本地导出工具：TXT / Markdown / JSON，支持图片、文件、语音、视频、本地语音转文字和聊天预览，面向 GPT、Claude、Gemini 等 LLM。 | Local-first WeChat chat exporte

Local editor for importing, managing, running, and injecting APM-backed assistant packages.

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

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

llama.cpp in pure Go

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI,

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable

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

🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers

AI-powered Vibe Investing for NASDAQ, S&P500 & crypto: LLM quant trading tools, multi-agent backtesting, and data-driven market columns (mNA

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

Open-source desktop coding agent where a lead model plans and cheaper models handle search, edits and review.

本地优先的视频→结构化笔记服务：B站/抖音/本地视频，平台字幕+本地离线转写，LLM 生成带时间轴笔记；桌面应用 / MCP / Agent Skill 三种接入。

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history,

Open-source EPUB reader and remote library client for Android, with a Kindle-inspired reading experience