Havuz

Open-source text-to-SQL engine you tune and measure on your own database

AI-native construction estimating platform for intake, takeoff, pricing, scheduling, knowledge, and quotes.

Continual harness optimization

Long-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and gov

绿群日报——绿群保研信息提炼：帮你每日快速跟进

Dev-only Rails engine that plugs AI coding agents into your running app: MCP introspection tools + stack-matched skills from companion gems

Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario

标书匠 BidCraft · 对话式标书编制系统：AI 智能编制技术标，支持招标文件解析、标段选择、标书编写、知识库提炼与学习对话式改稿。LLM-Wiki 路线，基于LangGraph实现。Open-source AI agent for construction tender

Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts)

Instella MoE is a fully open state-of-the-art Mixture-of-Experts language model, trained end-to-end on AMD Instinct™ GPUs.

Autonomous multi-agent framework to optimize scientific software

Forge a working, testable, publishable MCP server in 30s. TypeScript or Python, with example tools, the Inspector and tests included.

Real-world percentile benchmark for LLM inference servers: 1% A/B resolution, offline HTML reports. I am now on X also: https://x.com/bkuype

把 DeepSeek Harness 打包成能直接装的安卓 APK：不用 Termux、不用 root、不用配电脑，读屏/点按/虚拟屏/定时任务和整套技能都随包；它还能在手机上自己编译、打包、签名、发布。 Android APK for DeepSeek Harness — no

AI agent orchestration for open and closed source — a fully customizable fleet of AI agents covering every level of project maintenance, fro

简明技术中文 / Simplified Technical Chinese: a controlled language for Chinese technical writing, modelled on ASD-STE100. 40 rules, a one-meaning-

neatroots: see, check and replay your AI agent's runs on your machine while you build it. Local-first, by Neatlogs.

Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.

Mechanical Governance for LLM Decisions — model-agnostic governance regimes (R1/R2/R3), hard gates, entropy commit-reveal and governance met

The open-source legal AI agent. Documents stay on your disk and redlines arrive in Word as tracked changes. Fork of OpenCode.

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

🌿 StoryMoss (草苔) — AI导演式小说创作系统。Tauri+Rust驱动的桌面写作软件，集成知识图谱、伏笔追踪、StyleDNA风格引擎、协同编辑、7阶段全自动创作工作流。让AI成为你的创作搭档，越写越懂你。

Self-hosted studio for generating, previewing, binding, and shipping executable AGenUI interfaces with AI agents.

Make Claude Opus, Sonnet, GPT, or Gemini produce work close to what Claude Fable 5 would ship. 21 craft standards written and audited by the

Synapse — Temporal knowledge graph memory for AI agents. Self-hosted FalkorDB + Graphiti with hippocampus-layer memory management.

Markdown that steers an LLM is code. Genesis is the architectural layer for designing multi-agent, multi-skill systems -- with named pattern

Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable syst

Multi-tenant LLM API gateway for Claude and Codex — single Go binary, USD wallet, Alipay top-up, per-token caps, status-page health, fumadoc

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i

一条命令，把微信变成任何 AI Agent 的入口 | Connect WeChat to any AI Agent with one command

AI Skills That Actually Do Things — 中文優先的 Claude Code / Codex agent skills 合集 · Reusable bilingual skills for any LLM workflow

Zero Code Studio 是一个工程化 AI 代码生成平台，基于 Spring Boot、LangChain4j、LangGraph4j，支持工具调用、Workflow 编排、任务计划规划、三层上下文压缩、SSE 过程可视化、定点修改与一键本地部署。

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

The memory and context-management layer for production AI agents. 95.6% on LongMemEval, 93.2% on LoCoMo, with an open harness. Python + JS S

Comprehensive illustrated notes for Stanford CS336 (Spring 2025) — Language Modeling from Scratch. Live: qihongruan.github.io/cs336/

Emotional drive system for AI personas — 15-dimension sidecar that evolves in real time based on conversations and sleep cycles

🐾 TokenToll: is a self-hostable billing infrastructure for LLM APIs and SaaS products. Drop-in SDKs for Node.js and Python, YAML-defined pri

Entry point for AMALIA related resources.

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, rech

Open benchmark on observability tasks built on Harbor

Meet JevEmbed — turn embeddings into decisions. Choose, score, and judge with your choice of embedding model.

A decision cache for TypeSafe Jev-class models — memoize decisions so repeats are free, deterministic, and shareable. One 2 MB binary.

Multi-Agent Collaboration Design Patterns Built on LangGraph with 10+ battle-tested patterns, each with complete code, architecture

Hivekeep is a self-hosted platform of autonomous, persistent personal AI agents. Your AI team. At home.

A Claude Code skill for web report decks — richer ECharts charts, one file per slide (edit one page, save tokens), and complex structure dia

One-shot LLM eval cases by NAGI STUDIO - same prompt, different agents (model + harness), runnable artifacts side by side.

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker

This project is an AI Agent orchestration platform. It uses an LLM-driven decision engine, combined with capabilities (built-in tools, MCP p