Havuz

Rust-native, library-first coding-agent runtime and terminal CLI inspired by Pi, with composable LLM providers, tools, sessions, and plugin

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall

An evolving AI brain for Home Assistant

A dependency-free C inference engine for Liquid AI's LFM2 / LFM2.5 models. Terminal chat, an OpenAI-compatible server, a web agent and a ter

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

Feel how fast a local LLM runs before you buy the hardware

📊 电商数仓智能问数 AI Agent，最适合用于系统学习 LangGraph 的实战项目：基于 LangGraph、FastAPI、Qdrant、Elasticsearch、MySQL 与 React，完整实现元数据知识库、混合检索、自然语言生成 NL2SQL 生成校验、SQL

jevals, agent trace'lerini eval ve guardrail kontrollerinden tek istekte geçirerek production veya agent loop içinde değerlendirmeyi amaçlayan bir Python kütüphanesidir.

Neden yükseliyor · 7 günlük bir repoda 97 yıldız, 5 commit ve 4 farklı yazar erken ilgi ve katkı işareti. Tek istekte birden fazla kontrol, düşük maliyet ve agent loop'a uygun hız iddiaları dikkat çekiyor; performans ve maliyet rakamları README'de verilmiş, bağımsız doğrulama olarak kabul edilmemeli.

High-performance Go proxy gateway for 9Router LLM routing — 32K RPS, 42MB RAM, CGO-free

Multi-agent pipeline that turns a research topic into a draft paper grounded in real literature, with citation hallucination detection and c

Self-hosted dashboard for all your AI plans. Track limits, resets and spend across Claude, Codex, Cursor, Copilot, Grok and more.

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.

Understand Your Agents. Turn agent logs into interactive maps and stories. Explore decisions, replay the work, and get answers linked to the

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

RAM efficient terminal agent harness for coding, cybersecurity, and automation.

Wemux - self-hostable AI agent collaboration platform (Apache-2.0, community edition)

T3Code, but in your terminal

DSH插件市场 / DSH Plugin Marketplace: 在 DeepSeek Harness Web GUI 中一键浏览、安装与更新 GitHub topic:dsh-plugin 的全部插件 | browse, install & update all GitHub

The open source AI coding agent, in Rust. CLI, TUI and HTTP server for local AI agents — no Docker required.

A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-tea

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

Open-source, local-first AI video clipper. Long video in, caption-burned speaker-tracked 9:16 clips out. Fully offline with Whisper + Ollama

Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

Hermes Agent context engine: the main model writes the compaction handoff on its cached prompt prefix

A local AI agent built from scratch in Python with Ollama: conversation memory, system prompts, and multi-step tool calling.

"CatchMe: Make Your AI Agents Truly Personal"

Unified LLM access layer in Rust — one API for 325 AI providers. 统一 LLM 服务接入层：一套 API 接入 325 家 AI 服务商。

Multi-model council for DeepSeek Harness: independent answers, anonymous peer reviews, and an inspectable final decision.

The missing bridge between your ML models and your AI agents.

考公刷题 App（公考/gongkao/国考/省考/事业单位）：行测 申论 题库 · 错题本 · AI 解析。中文名：没钱考什么公。

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augment

LoopArena, uzun süreli yazılım görevlerinde bir coding agent’ı yönlendiren modelleri ortak koşullarda karşılaştırmak için benchmark ve çalıştırma altyapısı sunuyor.

Neden yükseliyor · Coding agents’ın uzun süreli iş akışlarında nasıl yönlendirileceği güncel bir araştırma konusu; LoopArena bu konuya açık protokol, benchmark sonuçları ve bir arXiv paper ile dikkat çekiyor. Ancak 146 yıldız, 28 günlük repo yaşı ve son 28 günde tek farklı yazar, ilginin henüz yaygın benimsemeye dönüştüğünü göstermiyor.

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark,

Mutual-credit coordination for contributing spare LLM subscription capacity through GitHub issues and pull requests.

A performant markdown library for iOS & macOS that supports streaming

Not Ai isn’t just about bypassing AI detectors. It puts good writing first, creating clear, honest prose shaped by human writing standards.

Review what your coding agent changed, without leaving Rex. Think herdr-reviewr, but for Rex.

Forgot a command? psst your terminal what you need and get the exact command for your system, ready to go.

ARTEX ：AI 自主渗透测试系统（Go + Next.js），基于 Autumn-27/ARTEX v0.3.15（e6ec569，AGPL-3.0）。原版 v0.3.15 下载说明与恢复指引见 README。

Agent dashboard runs reliability scans, skills, and network access probes.

On-device meeting capture, dictation, and vault-native knowledge layer for macOS. Nothing leaves your Mac.

Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.

Where terminal agents work together. Claude Code, Codex, Copilot CLI and pi on the same task, in one mission, each keeping its own TUI in a

RikkaHub Agent · Pure — an Android AI agent that survives long runs. Independent hardening pass on the rikkahub on-device agent: usage ledge

Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + ve

Your First LLM-Wiki Conversation Knowledge Base

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH

FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready.