* [atomic-agent v0.4.0](https://github.com/AtomicBot-ai/atomic-agent) – Local operator agent for llama.cpp that controls browser, files, shell, tasks, and approvals while keeping data and models local.

* [Crush v0.91.0](https://github.com/charmbracelet/crush) – Terminal-based AI coding assistant supporting multiple LLMs, sessions, and extensible capabilities.

* [Agenta v0.113.0](https://github.com/Agenta-AI/agenta) – LLMOps platform offering integrated prompt playground, prompt management, evaluation, and observability for building reliable LLM applications.

* [RuFlo v3.38.19](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [agent-relay v11.8.0](https://github.com/AgentWorkforce/relay) – Real-time messaging between AI agents.

* [OSpec.ai 2.0.0](https://github.com/clawplays/ospec) – Document-driven development workflow enabling spec-driven AI coding assistants and CLI-based change management.

* [MoAI-ADK v3.1.0](https://github.com/modu-ai/moai-adk) – High-performance AI development environment that automates TDD and DDD workflows and coordinates specialized agents for Claude Code.

* [Qwen Audio Agent v1.10.0](https://github.com/QwenAudio/qwen-audio-agent) – A realtime voice runtime for AI agents that keeps them talking and working through an audio agent architecture.

* [Memmy v1.1.0](https://github.com/MemTensor/memmy-agent) – Memory hub and local agent runtime that provides shared long-term personal context across multiple AI agents.

* [DentalPin v2.4.0](https://github.com/dentalpin/dentalpin) – API-first dental clinic management platform with patients, odontograms, scheduling, treatment plans, billing, and a built-in agentic AI copilot.

* [ChatbotX v1.4.0](https://github.com/ChatbotXIO/ChatbotX) – Omnichannel chatbot platform for agentic workflows via APIs, CLI, and MCP.

* [Kelos v0.53.0](https://github.com/kelos-dev/kelos) – Kubernetes-native framework for orchestrating autonomous AI coding agents.

* [(S)AGE v11.19.0](https://github.com/l33tdawg/sage) – Persistent, consensus-validated institutional memory infrastructure for AI agents with confidence scoring and natural decay.

* [Dive v1.26.0](https://github.com/deepnoodle-ai/dive) – Foundational Go library for building AI agents and LLM-powered applications with multi-provider access, tool calling, and a robust agent loop.

* [Kandev v0.91.0](https://github.com/kdlbs/kandev) – Kanban-based development environment that orchestrates multiple AI agents, reviews changes, and manages parallel tasks.

* [Strands Agents python/v1.53.0](https://github.com/strands-agents/harness-sdk) – Model-driven SDK for building and running AI agents, with customizable agent loops, multi-agent workflows, and model-agnostic providers.

* [Sortie v1.21.0](https://github.com/sortie-ai/sortie) – Agent orchestrator that turns tracker issues into isolated, parallel autonomous agent sessions with persistent state, retries, CI feedback, and cost tracking.

* [AgentHound 1.1.0](https://github.com/adithyan-ak/AgentHound) – Offensive security framework for AI agent infrastructure that runs recon, credential and model inventory, exploitation, and builds a Neo4j graph to analyze attack paths.

* [agent-device v0.20.10](https://github.com/callstack/agent-device) – CLI for automating and inspecting iOS, Android, TV, and desktop apps to verify app behavior for AI agents.

* [oh-my-opencode-slim v2.2.15](https://github.com/alvinunreal/oh-my-opencode-slim) – Lightweight, low-token OpenCode agent-orchestration plugin that delegates tasks to specialized sub-agents and manages multi-step workflows.

* [HashCortX v2.5.0](https://github.com/Hash-7777/HashCortX) – Local-first macOS AI workspace combining multi-provider chat, autonomous coding agents, multi-agent swarms, specialist agents, and financial and security tools.

* [Flare v1.1.0](https://github.com/AlgoNoRhythm/Flare) – Graph-first IDE that maps a codebase into a live dependency graph with lenses, snapshots, and an embedded agent terminal.

* [Containarium v0.66.0](https://github.com/FootprintAI/Containarium) – Run hundreds of isolated Linux development environments on a single VM using LXC, SSH jump hosts, and ZFS-backed persistence.

* [Nimbalyst v0.75.3](https://github.com/nimbalyst/nimbalyst) – Visual workspace for building and collaborating with coding agents across files, sessions, and tasks.

* [Secure MCP Tunnel client v0.0.13](https://github.com/openai/tunnel-client) – Secure MCP Tunnel customer-run client that connects a private MCP server to ChatGPT, Codex, and related APIs via an OpenAI-hosted tunnel endpoint.

* [copperhead v0.10.0](https://github.com/copperheadhq/copperhead) – AI agent that designs, documents, and validates real PCBs from prompts by editing KiCad repositories and running ERC and DRC checks.

* [OpenChatCut v0.2.11](https://github.com/0xsline/OpenChatCut) – An agent-native, local-first AI video editor that generates and edits fully editable multi-track timeline projects with MCP integration and production-ready exports.

* [DeepSeek Harness Control Center v0.3.0](https://github.com/feibi-mochi/deepseek-harness-control-center) – DeepSeek Harness monitoring UI for live balances, token and cost breakdowns, completion alerts, recharge shortcuts, and host-gated session controls with draggable responsive layout.

* [TrueForge charts/trueforge@0.1...](https://github.com/truefoundry/trueforge) – TrueForge is an agent harness that runs the execution loop with model calls, MCP tools, skills, sandboxing, approvals, and session state via chat UI and APIs.

* [Agent-Safe Pipeline v0.1.2](https://github.com/decionis/agent-safe-pipeline) – Reference architecture for safely executing AI-agent proposed actions via an independent authorization boundary with intent capture, policy decision, human verification, and a gated single-use executor.

* [Sidecar v0.99.1](https://github.com/marcus/sidecar) – Terminal dashboard for AI coding agents providing git diffs, file browsing, conversation history, and TD-based task management.

* [Pane v2.4.80](https://github.com/dcouple/Pane) – Terminal-first agent manager that runs any CLI AI agent, manages worktrees, and centralizes agent workflows.

* [AI Maestro v0.36.43](https://github.com/23blocks-OS/ai-maestro) – Agent orchestrator providing persistent memory, agent-to-agent messaging, and a dashboard to manage agents across multiple machines.

* [AgentField v0.1.135](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Kane CLI 0.8.6](https://github.com/LambdaTest/kane-cli) – Validation layer for AI coding agents and natural-language browser automation that launches Chrome and returns structured run results.

* [Juggler v0.5.8](https://github.com/juggler-ai/juggler) – A visual AI coding agent with a local, shared tree-based session, inspectable tool calls, and plugin-driven UI and orchestration.

* [Agent SDK for Go v0.3.5](https://github.com/agenticenv/agent-sdk-go) – Temporal or Restate-backed Go SDK for running AI agents durably, with pluggable components for state, tool calls, and execution loops across restarts.

* [Pi Agent Desktop v0.1.14](https://github.com/DLYZZT/pi-desktop) – Local-first Electron desktop workspace for managing Pi Coding Agent sessions, project files, browser tools, skills and plugins, with messaging integrations via Telegram and Lark.

* [Sympozium v0.10.48](https://github.com/sympozium-ai/sympozium) – Kubernetes-native platform orchestrating fleets of AI agents that diagnose, scale, and remediate clusters.

* [Autopus-ADK v0.50.108](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [Agent Go SDK v0.2.66](https://github.com/Ingenimax/agent-sdk-go) – Powerful Go framework for building production-ready AI agents with memory, tool execution, multi-LLM support, and enterprise features.

* [DentalPin v2.3.1](https://github.com/martinezsalmeron/dentalpin) – API-first dental clinic management software with modular scheduling, patient records, treatments, billing, and a built-in agentic AI copilot.

* [UiPath TypeScript SDK 1.6.2](https://github.com/UiPath/uipath-typescript) – TypeScript SDK providing type-safe access to UiPath Platform services for browser and Node.js applications, including OAuth and secret-based authentication.

* [EverFern v1.1.6](https://github.com/Everfern-AI/Everfern) – Local desktop AI agent that plans and executes computer actions, including browser research, with sandboxed execution and persistent memory.

* [Rove v0.8.196](https://github.com/Sma1lboy/rove) – Terminal-native workspace that runs multiple coding tasks in parallel using isolated git worktrees and persistent agent or shell sessions.

* [Wanta v0.1.177](https://github.com/oomol-lab/wanta) – Wanta is a desktop AI agent foundation that provides an agent runtime, local tools, permission controls, connected services, and artifact-based workflows.

* [agent-inspect @agent-inspect/vites...](https://github.com/rajudandigam/agent-inspect) – Local evidence debugger for TypeScript AI agents that turns runs into execution trees for debugging, regression checks, and share-checked offline artifacts.

* [AgentSphere v1.0.70-alpha](https://github.com/nullpointexception-i/agent-sphere) – LLM-driven AI agent orchestration platform that coordinates a perception–planning–execution–feedback loop with tool, MCP, CLI, and browser capabilities.

* [Grix v3.2.4+869](https://github.com/askie/grix) – Mobile and desktop chat app for DeepSeek Harness and other coding agents, managing agents as contacts and enabling shared threaded collaboration with controls and approvals.

* [K8E v1.35.5-20260824-rc3...](https://github.com/xiaods/k8e) – Lightweight CNCF-conformant Kubernetes distribution optimized for rapid deployment, enterprise high-availability, and secure AI agent sandboxing.

* [SAM: Sovereign Agent Mesh v0.1.0-alpha.7](https://github.com/google/sam) – Sovereign Agent Mesh is a zero-config, zero-trust P2P network that enables autonomous AI agents to plug in and discover tools dynamically via lightweight nodes.