Havuz

Local-first adaptive tutoring agent foundation reference implementation for iOS and Web, with a civil-service exam application.

Open-source, token-frugal agents for real teams — private memory, shared packs, your hardware.

Model Shell Protocol: an application-owned command runtime that gives AI agents OS-like workspace semantics.

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

Top Open-Source AI Engineering Platform 2026 Qyvaria Kernel

Lynn GitHub 镜像仓 · Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· 主仓 https://github.com/MerkyorLynn/Lynn · 下载 https:

A structured agent runtime for LLMs. Structured context, multi-stage workflows, and ECS-based orchestration in a single binary

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

Brigade, kullanıcının kendi makinesinde çalıştırabildiği, ortak kalıcı belleğe sahip birden fazla AI agent’ı koordine eden bir runtime ve araç ekosistemidir.

Neden yükseliyor · 100 günlük yaşına rağmen 6.779 yıldız ve son 28 günde 87 commit dikkat çekici ilgi ve geliştirme temposuna işaret ediyor; kişisel agent’ları self-hosted, çok kanallı ve ekip halinde çalıştırma fikri de güncel AI agent ilgisiyle örtüşüyor. Yükselişin kesin nedeni yalnızca bu verilerden belirlenemez; commit’lerin 5 farklı yazardan gelmesi aktivitenin varlığını gösterse de katkı tabanı hâlâ sınırlı.

Durable local workflows for agent loops: plans, evidence, objective gates, checkpoints, and dashboards for coding agents.

DataFoundry is an open-source AI workbench for data analysis, unifying data sources, knowledge, tools, and agent runtime into a governed wor

croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and en

Local-first AI interactive fiction app — a self-hosted narrative engine with an async multi-agent brain that keeps story state in plain file

Open-source managed runtime for OpenAI Codex, Claude Agent SDK, OpenCode, and Pi Agent. Run coding agents through one Agents API with isolat

小丑鱼（Clownfish）：本机优先、带长期记忆的 AI 工作应用，支持对话、能力任务、办公文件与持续工作。

Assessment-driven, local-first learning agent built on an observable Agent Runtime and eval harness—grounded ingestion, trace replay, HITL a

为 Token 燃烧而生：token 越来越便宜，质量永远稀缺——与其省 token，不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优，用冗余换质量。Go 写的开源终端 Coding Agent，类 Claude Code，可接入任意模型，对团队友好

An open source AI roleplay agent harness. One click builds an autonomous character agent that creates with you. Websites, code, music, video

Ghost-ALICE OS: agent governance for intent, scope, evidence, and runtime state

Runtime-neutral AI execution bridge for Claude Agent SDK, Codex app-server, and Agent Client Protocol (ACP).

Apache Maka, agent görevlerini Desktop, TUI ve CLI üzerinden çalıştıran ve her adımı kalıcı bir event log içinde tutan bir agent workspace’tir.

Neden yükseliyor · 123 günlük bir repoda 5.665 yıldızın yanı sıra son 28 günde 769 commit ve 23 farklı yazar görülüyor; bu, ilgiyi tek başına yıldız sayısından daha iyi destekleyen güçlü bir aktivite sinyali. Apache Incubator bünyesinde olması ve benchmark sonuçlarıyla görev kayıtlarını yayımlama yaklaşımı da dikkat çekiyor; ancak bu ölçümlerin bağımsız doğrulama düzeyi verilen bilgilerden anlaşılamıyor.

Build and supervise scheduled AI workers with an open-source runtime, human approvals, run logs, REST API, and MCP tools.

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. I

Run your own AI team from your phone. Claude Code, Codex and more on your own server: shared tasks, always-on agents, a small composable bas

AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

Pluggable extension packages for the Pi AI-agent runtime. Each package exposes LLM-callable tools via MCP — covering IM workspace integratio

CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

Run any AI agent — Claude Code, GAP, LangGraph DeepAgents — in a hermetic sandbox. Reference implementation of the Harness Protocol.

半人马环 Centaur Loop：AI 员工的最小工作单元框架。把复杂岗位拆解为可由 AI 接管、由人类治理、由反馈和记忆持续进化的循环工作流 / The smallest work unit for building AI employees.

Open-source enterprise agent platform affinitised to Huawei Ascend (NPU) + Kunpeng (ARM64 CPU). For self-hosted, governance-gated, multi-ten

Gini Agent, kalıcı hafıza ve görev yürütme özelliklerini ortak bir runtime üzerinden sunan kişisel bir AI agent yazılımıdır.

Neden yükseliyor · 145 günde 2332 yıldız, projeye belirgin bir ilgi olduğunu gösteriyor; kalıcı hafızalı kişisel agent ve ortak runtime yaklaşımı bu ilginin olası nedeni. Ancak son 28 günde commit ve farklı yazar sayısı sıfır olduğundan ilginin hâlen sürdüğünü veya geliştirme temposunu doğrulayan veri yok.

Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with

Self-hosted gateway for Claude Code, Codex, Antigravity, Grok Build, OpenCode. Run AI coding agents on your own infra with a shared local-fi

Decision Infrastructure for the AI Era. 🧠✨️🤺

Parallel ai-agent sessions in one panel, with permission-aware tools, preflight conflict checks.

Rust-first, local-first multi-agent runtime with a desktop HUD, policy-gated tools, voice, and worktree-isolated coding agents.

Hermes Agent-focused architecture and runtime health checks

Markdown that runs — one file, any agent.

Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a

the governed runtime for agent skill workflows, off the leash but on the record

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

Deterministic safety solutions for probabilistic AI agents

Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agent

A governed, local-first AI agent for enterprise Chat, Workflows, Associate, and MCP-connected business systems.

A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills.

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless re

Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistra

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