* [ByteRover CLI v3.16.0](https://github.com/campfirein/byterover-cli) – Interactive REPL CLI providing persistent, structured memory and context-tree management for AI coding agents, with cloud sync and multi-LLM support.

* [Clauge v3.0.0](https://github.com/ansxuman/Clauge) – Single-window developer workspace combining coding agents, API client, SQL/NoSQL editors, SSH, file explorer, and per-mode AI assistants.

* [MCP Toolbox for Databases v1.3.0](https://github.com/googleapis/mcp-toolbox) – MCP server connecting AI agents, IDEs, and applications to enterprise databases with prebuilt and customizable tools.

* [WeKnora v0.6.0](https://github.com/Tencent/WeKnora) – LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using the RAG paradigm.

* [Claude Code Skills for production-ready Golang projects v1.5.0](https://github.com/samber/cc-skills-golang) – Go-focused agent skills for coding assistants covering language, testing, security, observability, and related best practices.

* [Eliza v2.0.1](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [Headroom v0.22.0](https://github.com/chopratejas/headroom) – Context-compression layer reducing LLM input tokens by compressing tool outputs, logs, files, and RAG chunks while preserving answers.

* [hoop.dev 1.83.0](https://github.com/hoophq/hoop) – Proxy that secures and simplifies access to infrastructure with outbound-only connections and integrated SSO.

* [Cherry Studio v1.9.9](https://github.com/CherryHQ/cherry-studio) – Desktop client supporting multiple LLM providers, available on Windows, Mac, and Linux.

* [altimate-code v0.8.0](https://github.com/AltimateAI/altimate-code) – Deterministic data engineering harness offering SQL analysis, column-level lineage, dbt integration, FinOps, and multi-cloud warehouse connectivity.

* [OpenCode Manager v0.12.0](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.

* [OpenClaw Mini v0.1.0](https://github.com/voocel/openclaw-mini) – Minimal core agent architecture reproduction covering session-key domains, serialized queues, tool-based memory retrieval, on-demand context loading, extensible skills, and active heartbeat wake.

* [Spectrum v1.18.0](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.

* [OpsKat v1.7.0](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.

* [Reasonix desktop-v0.54.0](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.

* [runline v0.8.0](https://github.com/Michaelliv/runline) – Code-mode agent environment that runs JavaScript in a QuickJS WASM sandbox to call API plugins.

* [Memori v3.3.6](https://github.com/MemoriLabs/Memori) – Agent-native memory infrastructure: SQL-native, LLM-agnostic layer that turns agent execution and conversations into structured persistent state.

* [MemOS v2.0.17](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.

* [CoStrict v2.8.4](https://github.com/zgsm-ai/costrict) – Enterprise-focused AI coding assistant providing standardized code generation, repository-wide code review, context-aware completion, and private deployment support.

* [OpenClacky v1.2.0](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.

* [Garden Skills web-design-engineer-...](https://github.com/ConardLi/garden-skills) – Curated set of production-ready agent skills for Claude Code, Cursor, Codex, and other AI coding agents.

* [OpenCodeReview v1.1.10](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.

* [SoloMD v4.4.2](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.

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

* [UnicomAI/wanwu v0.5.5](https://github.com/UnicomAI/wanwu) – Enterprise-grade multi-tenant platform for developing large model applications including intelligent agents, workflows, and text Q&A with model management.

* [Nuwax v1.1.10](https://github.com/nuwax-ai/nuwax) – Build and deploy private agentic AI solutions using a no-code, one-stop platform.

* [Mobile Next - MCP 0.0.57](https://github.com/mobile-next/mobile-mcp) – Model Context Protocol server enabling platform-agnostic mobile automation and device interaction via accessibility snapshots or screenshot-based actions.

* [F5 NGINX Agent v3.10.3](https://github.com/nginx/agent) – Companion application for remote management, configuration, and real-time metrics collection from NGINX instances.

* [ClawX v0.4.7](https://github.com/ValueCell-ai/ClawX) – Desktop interface for OpenClaw AI agents that turns CLI orchestration into a graphical, cross-platform app with scheduling, channel management, and extensible skills.

* [Skybridge v1.0.3](https://github.com/alpic-ai/skybridge) – Fullstack TypeScript framework for type-safe, React-powered ChatGPT apps with zero-config dev tools and HMR.

* [HarnessClaw Engine v0.0.15](https://github.com/harnessclaw/harnessclaw-engine) – LLM programming-assistant engine in Go supporting WebSocket, multi-turn dialogues, tool calling, permission control, and skill extensions.

* [OpenAgent v1.1.2](https://github.com/Haohao-end/openagent) – End-to-end platform for building, orchestrating, publishing, and operating AI agents with visual workflows and dataset management.

* [AxonHub v0.9.43](https://github.com/looplj/axonhub) – Modern AI gateway providing unified OpenAI, Anthropic, and AI SDK-compatible APIs with tracing, project management, and developer tools.

* [TencentDB Agent Memory v0.3.5](https://github.com/Tencent/TencentDB-Agent-Memory) – Local four-tier progressive memory system providing layered long-term and symbolic short-term memory for AI agents without external API dependencies.

* [Agentica, AI Function Calling Framework v0.45.1](https://github.com/wrtnlabs/agentica) – Agentic AI framework specialized in AI Function Calling using TypeScript classes, OpenAPI, and MCP protocols.

* [Memoh v0.9.1](https://github.com/memohai/Memoh) – Multi-member, containerized AI agent platform with per-bot isolated containers and structured long-term memory for chat.

* [Cyrus v0.2.61](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.

* [AgentField v0.1.87](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [archestra platform-v1.2.54](https://github.com/archestra-ai/archestra) – MCP-native centralized platform for orchestrating, securing, and observing MCP servers with private registry and cost controls.

* [open-slide @open-slide/cli@1.2....](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.

* [Jean v0.1.51](https://github.com/coollabsio/jean) – Desktop AI assistant for managing multiple projects, git worktrees, chat sessions, terminals, and GitHub integrations via Claude CLI.

* [Clanker CLI v0.0.8](https://github.com/bgdnvk/clanker) – CLI for querying infrastructure and services using read-only CLI/API calls and summarizing results.

* [Agentbaker v0.20260527.0](https://github.com/Azure/AgentBaker) – Components to provision Linux and Windows Kubernetes nodes, build VM images, and render node configuration for Azure.

* [Go Agent for the Internet Computer v0.8.3](https://github.com/aviate-labs/agent-go) – Golang library for interacting with Internet Computer replicas, providing Candid support, identity management, and certificate handling.

* [computer-use-linux v0.2.4](https://github.com/agent-sh/computer-use-linux) – Linux desktop control server and CLI for MCP hosts, offering AT-SPI accessibility, compositor-aware window targeting, screenshots, and input.

* [Docfork MCP dgrep-v0.2.2](https://github.com/docfork/docfork) – Fetches and serves live-synced, version-accurate documentation to prevent AI hallucinations and context bloat.

* [Hades agent-v1.1.1](https://github.com/chriskaliX/Hades) – Host-based intrusion detection system leveraging eBPF and netlink for kernel-level event monitoring.

* [psst v0.7.1](https://github.com/Michaelliv/psst) – AI-native secrets manager injecting secrets into subprocess environments so agents can use them without seeing values.

* [Manifest manifest@6.6.1](https://github.com/mnfst/manifest) – Backend framework enabling data, storage, logic, and admin panel definition in a single YAML file.

* [Arkloop v26.5.21.2](https://github.com/qqqqqf-q/Arkloop) – Design-focused AI agent platform offering multi-model routing, sandboxed execution, persistent memory, and a ready-to-run desktop app.

* [Proma v0.9.40](https://github.com/ErlichLiu/Proma) – Claude Agent SDK-based AI agent platform integrating chat apps and multiple LLM providers for proactive, workflow-ready power-user automation.

* [Tingly Box v0.260531.1](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.

* [mcp-use mcp-use@1.29.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [Agent-HTML v0.1.0-alpha.2](https://github.com/Sayhi-bzb/Agent-HTML) – AI-native workspace for turning generated HTML into structured, editable, previewable documents with block editing and agent feedback.

* [Wallfacer v0.0.7-alpha.11](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.

* [stagewise stagewise@1.3.1-nigh...](https://github.com/stagewise-io/stagewise) – Browser toolbar connecting frontend UI to AI agents for real-time code editing.

* [Voquill desktop-dev-v0.0.645](https://github.com/voquill/voquill) – Cross-platform AI voice-typing app that dictates into any desktop app, cleans transcripts with AI, and syncs a personal glossary.

* [OpenYida v2026.5.25](https://github.com/openyida/openyida) – Yida low-code app builder using AI for zero-config development and instant deployment.

* [ServerBee v1.0.0-alpha.2](https://github.com/ZingerLittleBee/ServerBee) – Lightweight self-hosted VPS monitoring system with agents, server, and web dashboard.

* [senpi v2026.5.20-4](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.