* [Agent Canvas v1.15.0](https://github.com/OpenHands/OpenHands) – Self-hosted developer control center that runs coding agents across local, remote, or cloud backends and automates everyday engineering workflows.

* [Claude Code Skills for production-ready Golang projects v2.0.0](https://github.com/samber/cc-skills-golang) – Go-focused agent skills for coding assistants covering language, testing, security, observability, and related best practices.

* [OpenCodeReview v1.10.0](https://github.com/alibaba/open-code-review) – AI-powered CLI that reviews Git diffs using LLM agents and deterministic pipelines to produce precise, line-level structured comments.

* [TencentDB Agent Memory v2.0.1](https://github.com/TencentCloud/TencentDB-Agent-Memory) – TencentDB Agent Memory provides symbolic short-term and layered long-term memory for AI agents to retain context and reduce token usage without external APIs.

* [Spectrum v12.8.0](https://github.com/photon-hq/spectrum-ts) – Unified TypeScript messaging SDK to write agent logic once and deploy across iMessage, WhatsApp, terminal, or custom platforms.

* [DOMD v0.7.0](https://github.com/do-md/domd) – WYSIWYG Markdown editor built on a 20KB, from-scratch Markdown-native engine for human editing and AI streaming.

* [Reasonix studio-v2.9.0](https://github.com/esengine/DeepSeek-Reasonix) – DeepSeek-native AI coding agent for your terminal, engineered around prefix-cache stability to keep token costs low across long sessions.

* [hoop.dev 1.150.0](https://github.com/hoophq/hoop) – Proxy that secures and simplifies access to infrastructure with outbound-only connections and integrated SSO.

* [OpenCode Manager v0.17.0](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [Minke v0.3.0](https://github.com/lencx/Minke) – Minke provides a local-first desktop workspace for DeepSeek Harness, keeping conversations, project files, terminals, web tools, and remote controls in a focused environment.

* [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.

* [Cherry Studio v2.0.9](https://github.com/CherryHQ/cherry-studio) – Desktop client supporting multiple LLM providers, available on Windows, Mac, and Linux.

* [Skybridge v1.4.1](https://github.com/alpic-ai/skybridge) – Fullstack TypeScript framework for type-safe, React-powered ChatGPT apps with zero-config dev tools and HMR.

* [mu v1.5.0](https://github.com/micro/mu) – Collection of small, privacy-focused web apps that avoid ads, algorithms, and tracking.

* [runline v0.28.0](https://github.com/Michaelliv/runline) – Code-mode agent environment that runs JavaScript in a QuickJS WASM sandbox to call API plugins.

* [Headroom v0.36.5](https://github.com/headroomlabs-ai/headroom) – Headroom compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach an LLM to reduce tokens while preserving answers.

* [Claude Code Haha v0.5.5](https://github.com/NanmiCoder/cc-haha) – Local cross-platform Claude-compatible client with TUI and desktop apps, multi-agent tooling and Telegram/Discord integrations.

* [mcp-use mcp-use@2.3.0](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [octo-agent v1.16.0](https://github.com/open-octo/octo-agent) – Private, self-hosted AI coding agent with a feature-rich toolkit across CLI, web, desktop, IM, VS Code, Obsidian, SDK, and mobile interfaces.

* [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.

* [SoloMD v4.11.19](https://github.com/zhitongblog/solomd) – Local-first Markdown editor with an integrated agent panel, bundled MCP endpoint, AI provider support, git-backed vault, and YAML-scheduled automation.

* [OpenScience v2.0.49](https://github.com/synthetic-sciences/openscience) – Model-agnostic AI workbench that loops through literature review, hypothesis building, code and experiment execution, and research write-ups in a browser workspace.

* [Cyrene-Agent v1.1.6](https://github.com/Playa-0v0/Cyrene-Agent) – Electron and TypeScript Live2D AI desktop agent with Cyrene-like chat, emotional interaction, and personalized memory using BGE-M3, TTS, and ASR on Windows.

* [Liyuan v1.5.2](https://github.com/weidu12123/Liyuan) – AI Agent-based roleplaying app with memory ledger, decision cards, custom dashboard, and worldlines, compatible with character sheets and worldbooks.

* [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.

* [Goink v1.4.2](https://github.com/sigpanic/goink) – Cross-platform desktop AI novel writing assistant with conversational prompting, automatic status tracking, and local semantic search over SQLite using ONNX and BGE embeddings.

* [altimate-code v0.9.7](https://github.com/AltimateAI/altimate-code) – Deterministic data engineering harness offering SQL analysis, column-level lineage, dbt integration, FinOps, and multi-cloud warehouse connectivity.

* [F5 NGINX Agent v2.46.8](https://github.com/nginx/agent) – Companion application for remote management, configuration, and real-time metrics collection from NGINX instances.

* [MemOS memos-local-plugin-v...](https://github.com/MemTensor/MemOS) – Memory operating system for LLMs and AI agents providing unified store/retrieve/manage, multi-modal long-term memory and skill reuse.

* [CharacterArc v1.18.5](https://github.com/uu201/character-arc) – Desktop writing tool that manages project settings, character relationships, outlines, and chapter drafting with multi-model AI agent workflows.

* [or v0.6.16](https://github.com/ktsoator/or) – Modular Go toolkit with provider-neutral language model access and stateful agent tool loops with typed streaming events.

* [Eliza pr-evidence-11](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [OpenClacky v1.5.11](https://github.com/clacky-ai/openclacky) – Creator-focused platform for packaging encrypted, white-labeled AI workflows into sellable Skills with built-in storefront and cross-platform distribution.

* [dsh-agent-team-gui v1.0.1](https://github.com/toolclub/dsh-agent-team-gui) – Persistent multi-model agent teams for DeepSeek Harness with per-member models, roles, tools, and bounded DAG workflow planning and inspection.

* [Super-Agent-Party v0.4.3](https://github.com/heshengtao/super-agent-party) – 3D AI desktop companion platform with modular LLM enhancements, multi-terminal deployment, and cross-platform compatibility.

* [The Pair v2.7.1](https://github.com/timwuhaotian/the-pair) – Automated pair-programming app where two AI agents cross-check code and collaborate with real-time monitoring.

* [OpsKat v1.13.1](https://github.com/opskat/opskat) – AI-first desktop app for managing remote infrastructure - servers, databases, Redis, MongoDB, and Kafka - with policy enforcement and full audit logging.

* [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.

* [Eve eve@0.45.2](https://github.com/vercel/eve) – Filesystem-first framework for building durable AI agents, placing core capabilities in conventional directories for easy inspection, extension, and operation.

* [Cyrus v0.2.69](https://github.com/cyrusagents/cyrus) – LLM-powered background agent that monitors issues, creates per-issue git worktrees, runs sessions, and streams rich updates to Linear, GitHub, GitLab, and Slack.

* [Cindy v0.1.64](https://github.com/makecindy/cindy) – Cindy is a local-first AI agent client monorepo that orchestrates harnesses, models, and tools across desktop and mobile apps.

* [Knote v1.1.57](https://github.com/1661169091kiwi/Knote) – Local-first, Feishu-style WYSIWYG Markdown editor with a built-in AI agent for drafting, reviewing, and exporting documents.

* [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.

* [Wegent wework-v0.2.6](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [Joanium v2026.822.0](https://github.com/Joanium/Joanium) – Local-first AI desktop agent that runs scheduled background tasks, supports multi-model chat, and can use real integrations via MCP.

* [open-slide @open-slide/core@1.1...](https://github.com/1weiho/open-slide) – Framework for agent-driven slide decks that renders React pages to a 1920x1080 canvas and handles authoring, preview, assets, and export.

* [chartr v0.2.4](https://github.com/rengwu/chartr) – Agent multiplexer that visualizes work as a star-map and coordinates agent sessions with contextual tickets and blockers.

* [Blade Code v0.10.98](https://github.com/echoVic/blade-code) – AI CLI and web UI coding agent with 20+ tools, MCP support, and configurable providers for model-driven coding workflows.

* [Wallfacer v0.0.24](https://github.com/changkun/wallfacer) – Self-operating engineering platform orchestrating autonomous coding agents across a task board with isolated sandboxes, live logs, diffs, cost tracking, and full oversight.

* [LobsterAI 2026.8.25](https://github.com/netease-youdao/LobsterAI) – 24/7 personal assistant agent that executes tasks, automates workflows, runs code locally or in a sandbox, and supports IM control.

* [ComputeSDK @computesdk/microsan...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [Coddy 0.9.79](https://github.com/coddy-project/coddy-agent) – Coddy is a distroless-friendly Go-based general-purpose agent harness with a ReAct loop, ACP/HTTP/Telegram interfaces, MCP and skills integration, and long-term memory.

* [Yao v1.0.0-rc17](https://github.com/YaoApp/yao) – Engine for event-driven, proactive, self-scheduling autonomous agents with scheduling, multi-agent orchestration, and built-in vector/graph retrieval.

* [DevWeek app-v0.1.5](https://github.com/JYYYYYT/dev-report-weekly) – Desktop app that uses AI to turn locally reviewed Git commits into editable weekly Markdown work reports, with commit filtering and checks.

* [senpi v2026.8.23](https://github.com/code-yeongyu/senpi) – Opinionated TypeScript monorepo fork of pi-mono that provides a curated coding-agent runtime with builtin extensions and core tweaks.

* [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.

* [Tingly Box v0.260827.0-rc1](https://github.com/tingly-dev/tingly-box) – High-performance desktop LLM proxy that unifies access to many models and providers via a single OpenAI-compatible API.