* [Claude-Mem v13.0.0](https://github.com/thedotmack/claude-mem) – Persistent memory compression system that preserves and summarizes context across Claude Code sessions for continuity.

* [Daytona v0.184.0](https://github.com/daytonaio/daytona) – Secure and elastic infrastructure enabling fast, isolated execution of AI-generated code with programmatic control.

* [Gemini CLI v0.45.0](https://github.com/google-gemini/gemini-cli) – Command-line AI workflow tool that connects to tools, understands code, and accelerates workflows.

* [PentAGI v2.1.0](https://github.com/vxcontrol/pentagi) – Autonomous AI-driven penetration testing platform that runs sandboxed attacks, orchestrates specialized agents, and produces detailed vulnerability reports.

* [oh-my-claudecode v4.14.0](https://github.com/Yeachan-Heo/oh-my-claudecode) – Multi-agent orchestration for Claude Code with autonomous, parallel, coordinated, pipeline and token-efficient execution modes, specialized agents, and real-time HUD visibility.

* [OneCLI v1.35.0](https://github.com/onecli/onecli) – Gateway that injects stored credentials into outbound agent HTTP requests, swapping placeholders for real keys so agents never see secrets.

* [Hermes Control Interface v3.6.0](https://github.com/xaspx/hermes-control-interface) – Self-hosted web dashboard for managing AI agent stacks with terminal, file explorer, session and cron management, system metrics, and multi-agent administration behind a password.

* [Open Design open-design-v0.9.0](https://github.com/nexu-io/open-design) – Local-first, web-deployable design workflow that turns your coding agent into an artifact-driven design engine with composable skills and design systems.

* [CLI Printing Press v4.20.0](https://github.com/mvanhorn/cli-printing-press) – Prints token-efficient, agent-focused Go CLIs with Claude Code skills and MCP servers by extracting APIs and syncing data to SQLite.

* [Kortix v0.9.0](https://github.com/kortix-ai/suna) – Autonomous company OS where Linux-sandboxed AI agents run code, manage files, and automate operations 24/7.

* [Agent Teams v2.3.0](https://github.com/777genius/agent-teams-ai) – Desktop app for orchestrating autonomous AI agent teams with messaging, code review, and kanban task management

* [ChatLab v0.23.0](https://github.com/ChatLab/ChatLab) – Private, local desktop app for analyzing and exploring chat histories using SQL and AI agents.

* [CAD Skills 0.2.0](https://github.com/earthtojake/text-to-cad) – Library of agent skills for generating, inspecting, exporting, and previewing CAD, robot, and fabrication files.

* [sem v0.7.0](https://github.com/Ataraxy-Labs/sem) – Semantic version control providing entity-level diffs, blame, and impact analysis via tree-sitter across ten programming languages.

* [Open Multi-Agent v1.5.0](https://github.com/open-multi-agent/open-multi-agent) – TypeScript-native multi-agent orchestration that decomposes goals into parallel task DAGs and synthesizes results.

* [Sphere SDK v0.8.0](https://github.com/unicity-sphere/sphere-sdk) – Equips autonomous economic agents with identity, wallet, peer-to-peer discovery, messaging, atomic trades, invoicing, and settlement.

* [Activepieces 0.84.0](https://github.com/activepieces/activepieces) – Extensible AI automation platform with a type-safe TypeScript framework and over 280 integrations for workflow building.

* [OpenPets v2.5.0](https://github.com/alvinunreal/openpets) – Cross-platform desktop pets showing AI coding agents' live status, progress, and test runs via MCP and integrations.

* [AgentOps v3.0.0](https://github.com/boshu2/agentops) – DevOps-style toolbox that preserves agent context, orchestrates workflows, and composes lasting knowledge between sessions.

* [AI Factory 2.13.0](https://github.com/lee-to/ai-factory) – CLI that configures AI agents, installs skills, and runs spec-driven AI development workflows.

* [RedBox v2.2.0](https://github.com/Jamailar/RedBox) – Xiaohongshu-focused automation AI tool for downloading posts, AI transcription and paraphrasing, account tracking/cloning, and AI-assisted content creation.

* [OpenCLI v1.8.0](https://github.com/jackwener/OpenCLI) – Universal CLI hub and AI-native runtime that turns websites, Electron apps, and local binaries into deterministic, scriptable command-line interfaces.

* [Open Computer Use v5.0.0](https://github.com/coasty-ai/open-computer-use) – Platform providing AI agents that perform browser, terminal, and desktop actions to automate multi-step workflows.

* [Watchfire v7.0.0](https://github.com/watchfire-io/watchfire) – Orchestrates AI coding agents with project-aware context, structured tasks, and isolated git worktrees for iterative code generation.

* [Agent Deck v1.9.0](https://github.com/asheshgoplani/agent-deck) – Terminal-based session manager for running, organizing, and switching between multiple AI coding agent sessions.

* [Veritas Kanban v4.3.0](https://github.com/BradGroux/veritas-kanban) – Local-first Kanban and AI-agent orchestration platform for developers to manage board-driven tasks, git worktrees, and autonomous coding workflows.

* [UPage v2.0.0](https://github.com/halo-dev/upage) – Large-model-based visual web page builder offering AI-assisted layout and HTML/CSS/JS export.

* [ClawApp v2.0.0](https://github.com/qingchencloud/clawapp) – Mobile chat client for OpenClaw AI agents supporting streaming conversations, image exchange, tool invocation, PWA and APK.

* [InsForge v2.1.0](https://github.com/InsForge/InsForge) – Agent-native platform enabling AI agents to autonomously build and manage full-stack applications with backend features.

* [OpenCode Swarm v7.48.0](https://github.com/zaxbysauce/opencode-swarm) – Architect-led plugin that runs an 11-agent gated pipeline for code generation, review, testing, and security.

* [Pneuma Skills v3.17.0](https://github.com/pandazki/pneuma-skills) – Co-creation infrastructure connecting humans and code agents with visual environments, skills, continuous learning, and distribution.

* [ZeroID v1.6.0](https://github.com/highflame-ai/zeroid) – Identity infrastructure that issues verifiable agent credentials, enforces delegated on-behalf-of chains, and enables real-time revocation.

* [Kandev v0.55.0](https://github.com/kdlbs/kandev) – Kanban-based development environment that orchestrates multiple AI agents, reviews changes, and manages parallel tasks.

* [SoulForge v2.20.0](https://github.com/proxysoul/soulforge) – Live dependency-graph code intelligence enabling codebase-aware AI agents to prioritize relevant files and reduce wasted work.

* [Agent Swarm v1.89.0](https://github.com/desplega-ai/agent-swarm) – Multi-agent orchestration platform that runs lead and worker AI coding agents in Docker, coordinating tasks, integrations, and persistent memory.

* [Network-AI v5.9.0](https://github.com/Jovancoding/Network-AI) – TypeScript/Node.js multi-agent orchestrator providing shared blackboard state, guardrails, budgets, and cross-framework adapters.

* [MCPProxy v0.35.0](https://github.com/smart-mcp-proxy/mcpproxy-go) – Desktop proxy enabling scalable tool discovery, major token savings, and quarantine of malicious upstream servers for AI agents.

* [AI Agent Automation v0.9.0](https://github.com/vmDeshpande/ai-agent-automation) – Developer-first, local-first workflow execution engine enabling deterministic, inspectable AI-driven automation.

* [vibecode-pro-max-kit v2.4.0](https://github.com/withkynam/vibecode-pro-max-kit) – Spec-driven coding harness that turns AI coding agents into self-improving engineering teams with persistent context and automated planning.

* [beagle v4.1.0](https://github.com/existential-birds/beagle) – Claude Code plugin marketplace offering 127 skills for code review, documentation, testing, architectural analysis, and git workflows across multiple languages and frameworks.

* [Pipelock v2.6.0](https://github.com/luckyPipewrench/pipelock) – All-in-one security harness for AI agents offering egress control, DLP, SSRF protection, prompt-injection scanning, and workspace integrity monitoring.

* [wmux v2.16.0](https://github.com/openwong2kim/wmux) – Native Windows terminal multiplexer with split panes, MCP browser automation, and multi-agent AI CLI support without WSL.

* [OmniRoute v3.8.7](https://github.com/diegosouzapw/OmniRoute) – AI gateway providing an OpenAI-compatible endpoint with multi-provider routing, load balancing, retries, rate limits, caching, and observability for cost-aware inference.

* [Rowboat v0.5.3](https://github.com/rowboatlabs/rowboat) – Local-first AI coworker that builds persistent, editable Markdown knowledge from emails and meeting notes to assist everyday work.

* [opencode-power-pack v0.2.0](https://github.com/waybarrios/opencode-power-pack) – Eleven Claude Code skills ported to OpenCode, including code-review, security-review, feature-dev, frontend-design and more, installable with one config line.

* [Duel Agents v0.1.0](https://github.com/2aronS/Duel-Agents) – IDE-native routing layer that runs prompts across multiple models and selects the cheapest winning response.

* [Spool v0.5.0](https://github.com/paperboytm/spool) – Local AI session library that collects and indexes Claude, Codex, Gemini, and OpenCode sessions into a searchable, browsable sidebar.

* [IRIS v1.3.0](https://github.com/201Harsh/IRIS-AI) – Local-first neural OS layer converting spoken intent into native OS actions, automation, and context-aware file and application management.

* [Warden v0.14.0](https://github.com/stephnangue/warden) – Runtime access gateway enforcing identity-based egress policies and issuing ephemeral credentials so workloads have no long-lived secrets

* [CRE Acquisition Orchestrator v2.8.0](https://github.com/ahacker-1/cre-acquisition-orchestrator) – Multi-agent AI framework for commercial real estate multifamily acquisitions from due diligence through closing.

* [Statewave v0.9.0](https://github.com/smaramwbc/statewave) – Memory runtime for AI agents providing durable, structured memories with compiled summaries, provenance-aware ranked retrieval, and token-bounded context.

* [Chorus v0.9.0](https://github.com/Chorus-AIDLC/Chorus) – Harness managing LLM agent sessions, task state, sub-agent orchestration, observability, and failure recovery for AI-human workflows.

* [Rampart v1.1.0](https://github.com/peg/rampart) – Security layer enforcing YAML policies for commands, file access, and network requests from AI coding agents.

* [Signet AI v0.128.0](https://github.com/Signet-AI/signetai) – Local-first identity, memory, and secret management for AI agents, providing portable state across sessions, models, and harnesses.

* [ainovel-cli v0.4.0](https://github.com/voocel/ainovel-cli) – Multi-agent CLI that coordinates AI agents for automated novel outlining, drafting, editing, and checkpointing.

* [gollem v0.25.0](https://github.com/m-mizutani/gollem) – Go framework for agentic AI applications with MCP-based tool support, automatic session handling, and conversational memory management.

* [AI Coding Project Boilerplate v0.23.0](https://github.com/shinpr/ai-coding-project-boilerplate) – Production-ready TypeScript boilerplate optimized for Claude Code, using specialized sub-agents to prevent context exhaustion.

* [Superset desktop-v1.11.0](https://github.com/superset-sh/superset) – Terminal for running and managing 10+ parallel CLI coding agents locally.

* [Claude Code Workflows v0.20.0](https://github.com/shinpr/claude-code-workflows) – End-to-end AI-assisted development workflows using specialized agents to plan, implement, and quality-check reviewable code.

* [Dograh AI dograh-v1.31.0](https://github.com/dograh-hq/dograh) – Self-hostable platform to build, run, and test voice AI agents using drag-and-drop workflows and telephony integrations.

* [mcpc v0.3.0](https://github.com/apify/mcpc) – Universal command-line client for the Model Context Protocol, providing persistent sessions, scripting, OAuth 2.1 support, JSON code-mode, and AI sandboxing.

* [Kontext CLI v0.8.0](https://github.com/kontext-security/kontext-cli) – Command-line tool that injects short-lived, scoped credentials into AI coding agent sessions and logs tool usage for audit.

* [CyberStrikeAI v1.6.19](https://github.com/Ed1s0nZ/CyberStrikeAI) – AI-native, Go-based penetration-testing copilot combining hundreds of security tools, MCP orchestration, and an agent that runs engagements via conversation.

* [AEGIS v0.1.0](https://github.com/Justin0504/Aegis) – Pre-execution firewall that classifies and enforces runtime policies for AI agent tool calls, with audit trails and human approvals.

* [anywhere-agents v0.7.0](https://github.com/yzhao062/anywhere-agents) – Opinionated portable AI-agent configuration providing synced defaults, review workflows, and safety hooks across projects and sessions.

* [AgentVibes v5.9.0](https://github.com/paulpreibisch/AgentVibes) – Text-to-speech integration adding professional voices and personalities to Claude Code, Claude Desktop, and OpenClaw.

* [KiwiFS v0.20.0](https://github.com/kiwifs/kiwifs) – Knowledge server exposing Markdown files with Git versioning, full-text and vector search, and an Obsidian-like web UI.

* [DAC v0.2.0](https://github.com/bruin-data/dac) – Dashboard-as-code for defining, validating, and serving dashboards from YAML and TSX with a semantic layer and AI agent.

* [Marinara Engine v1.6.0](https://github.com/Pasta-Devs/Marinara-Engine) – Local AI-powered chat, roleplay, and game engine offering plug-and-play setup.

* [Magic Context v0.21.0](https://github.com/cortexkit/magic-context) – Cache-aware infinite context with cross-session memory and background history compression for AI coding agents.

* [NTM - Named Tmux Manager v1.16.0](https://github.com/Dicklesworthstone/ntm) – Tmux-based session manager that spawns, coordinates, and monitors multiple AI coding agents in tiled panes.

* [AI Maestro v0.35.0](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.

* [PageAgent v1.8.2](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [agtop v0.4.0](https://github.com/ldegio/agtop) – Top-style terminal dashboard monitoring local AI coding agent sessions with live spend, token usage, context pressure, CPU, tool activity, and process details.

* [Opensteer v0.10.0](https://github.com/steerlabs/opensteer) – Global browser-control runtime providing CDP helpers, named sessions, profile tools, and browser interaction skills.

* [oh-my-agent cli-v7.0.0](https://github.com/first-fluke/oh-my-agent) – Portable multi-agent harness for .agents-based skills, workflows, and standards-aware agent teams across major AI IDEs.

* [AI Team OS v1.5.0](https://github.com/CronusL-1141/AI-company) – Multi-agent operating system that runs autonomous AI teams to execute, coordinate, and self-improve software projects.

* [Reader v0.2.0](https://github.com/vakra-dev/reader) – Production-grade web infrastructure for scraping, crawling, stealth browser sessions, proxy management, and clean markdown output.

* [Open Mercato v0.6.0](https://github.com/open-mercato/open-mercato) – AI-supportive, modular framework for building enterprise-grade CRM, ERP, and commerce backends with customizable modules and multi-tenant support.

* [Accessibility Agents v5.4.0](https://github.com/Community-Access/accessibility-agents) – Automated agents enforcing WCAG 2.2 AA accessibility across Claude, GitHub Copilot, Gemini, Codex, and MCP platforms.

* [Mirage v0.0.1](https://github.com/strukto-ai/mirage) – Unified virtual filesystem mounting diverse services and data sources under a single Unix-like tree for AI agents.

* [git-lrc v0.3.0](https://github.com/HexmosTech/git-lrc) – Free, unlimited AI-powered pre-commit code reviews that analyze diffs and flag bugs, security issues, and regressions before commits land.

* [Agent Vault v0.16.0](https://github.com/Infisical/agent-vault) – HTTP credential proxy and vault brokering API access for AI agents by injecting credentials at the network layer.

* [axe v1.10.0](https://github.com/jrswab/axe) – CLI for defining and running focused LLM agents via TOML, usable from pipes, cron, or git hooks.

* [9Router v0.4.18](https://github.com/decolua/9router) – Universal AI routing proxy that tracks quotas and automatically falls back to cheap or free models for uninterrupted coding.

* [NVIDIA NemoClaw v0.0.58](https://github.com/NVIDIA/NemoClaw) – Reference stack simplifying secure, always-on OpenClaw assistant execution on the NVIDIA OpenShell runtime.

* [claude-view v0.44.0](https://github.com/tombelieber/claude-view) – Live dashboard to monitor Claude Code sessions with real-time status, cost tracking, search, and sub-agent visibility.

* [cass-memory v0.2.11](https://github.com/Dicklesworthstone/cass_memory_system) – Provides persistent, cross-agent procedural memory by converting scattered session logs into structured, confidence-tracked rules.

* [Lumina Note v1.4.11](https://github.com/blueberrycongee/Lumina-Note) – Modern Markdown note-taking app with live preview, bidirectional links, LaTeX and Mermaid support, canvas, and AI assistant.

* [Uni-CLI v0.225.0](https://github.com/olo-dot-io/Uni-CLI) – Command-grade access layer exposing websites, desktop apps, CLIs, and system capabilities as searchable, self-repairing commands for AI agents.

* [TermCanvas v0.39.10](https://github.com/blueberrycongee/termcanvas) – Infinite canvas desktop app for visually managing terminals.

* [Shep v1.208.0](https://github.com/shep-ai/shep) – Run multiple AI coding agents in parallel, each in its own isolated git worktree with automated commits, pushes, and PRs.

* [ADHD v0.1.4](https://github.com/UditAkhourii/adhd) – Coding-agent skill that parallelizes divergent reasoning across isolated cognitive frames, then scores and prunes results for stronger ideation.

* [TanStack AI @tanstack/ai-svelte@...](https://github.com/TanStack/ai) – Type-safe SDK for building provider-agnostic, multimodal AI applications with chat, streaming, agent loops, and isomorphic tools.

* [Stash v0.2.11](https://github.com/alash3al/stash) – Persistent memory layer for AI agents that stores, recalls, consolidates, and learns across sessions using Postgres and an MCP server.

* [Aguara v0.22.0](https://github.com/garagon/aguara) – Security scanner for AI agent skills and MCP servers that detects prompt injection, data exfiltration, and supply-chain attacks via local static analysis.

* [Full-Stack AI Agent Template 0.2.10](https://github.com/vstorm-co/full-stack-ai-agent-template) – Production-ready FastAPI+Next.js template for building type-safe AI/LLM agents with streaming, auth, observability, multi-DB support, and 20+ integrations.

* [The Agent Guild v0.3.2](https://github.com/mathomhaus/guild) – Provides shared context, memory, and task coordination for AI coding agents via a single Go binary with local SQLite and hybrid keyword/semantic search.

* [Dexto @dexto/tui@1.8.0](https://github.com/truffle-ai/dexto) – Universal intelligence layer that orchestrates LLMs, tools, and data to build stateful, multimodal agentic applications.

* [MDA Open Spec v1.1.7](https://github.com/sno-ai/mda) – Markdown superset that compiles one source into multiple agent runtime document formats with typed relationships and Sigstore-backed integrity.

* [melisai v0.6.0](https://github.com/dmitriimaksimovdevelop/melisai) – Single-binary Linux performance diagnostics using eBPF/BCC that detects anomalies, computes a health score, and recommends sysctl fixes.

* [ClawRouter v0.12.196](https://github.com/BlockRunAI/ClawRouter) – Smart LLM router that locally routes requests to the cheapest capable model across 30+ providers, reducing inference costs.

* [CAIPE 0.4.18](https://github.com/cnoe-io/ai-platform-engineering) – Community-driven multi-agent platform engineering system providing persona-driven agents, knowledge retrieval, and integrations for platform operations.

* [tokenu v1.1.0](https://github.com/lirantal/tokenu) – Unix du-like CLI that counts token usage for files and directories.

* [bkit - Vibecoding Kit v2.1.19](https://github.com/popup-studio-ai/bkit-claude-code) – Claude Code plugin providing PDCA-based development workflows, systematic context engineering, CTO-led multi-agent orchestration, and intelligent code assistance.

* [Incognide v0.2.1](https://github.com/NPC-Worldwide/incognide) – Unified tileable workspace combining chat, code, documents, web browsing, and media with context-aware automations.

* [MyAgents v0.2.19](https://github.com/hAcKlyc/MyAgents) – Desktop AI agent workspace and task center with multi-provider runtimes, IM/chat integrations, and CLI/SDK tooling.

* [Harnessclaw v0.0.16](https://github.com/harnessclaw/harnessclaw) – Electron-based desktop application for managing, chatting with, and operating AI agents and skills.

* [NanoClaw v2.0.64](https://github.com/nanocoai/nanoclaw) – Lightweight AI assistant running Claude agents in isolated containers, with messaging integrations, memory, scheduled jobs, and Anthropic Agents SDK support.

* [AgentOS v0.9.17](https://github.com/framersai/agentos) – TypeScript runtime for AI agents providing cognitive memory, adaptive behavior, and runtime tool synthesis.

* [Spool v0.4.19](https://github.com/spool-lab/spool) – Local instant search across AI conversations, bookmarks, and 50+ services with agent-integrated querying.

* [The Pair v2.0.1](https://github.com/timwuhaotian/the-pair) – Automated pair-programming app where two AI agents cross-check code and collaborate with real-time monitoring.

* [Sandcastle v0.32.0](https://github.com/gizmax/Sandcastle) – Workflow orchestrator for AI agent pipelines defined in YAML, with multi-provider routing, integrations, and dashboard.

* [BoxLite v0.9.5](https://github.com/boxlite-ai/boxlite) – Lightweight VM substrate for running persistent, OCI-compatible container workspaces with hardware isolation and async-first APIs.

* [Autopus-ADK v0.50.0](https://github.com/Insajin/autopus-adk) – Harness that orchestrates multiple AI coding agents into engineering workflows with planning, testing, code review, and security audits.

* [remindb v0.3.0](https://github.com/radimsem/remindb) – Single-file SQLite memory for agents with token-efficient node hashing, temperature-based hot/cold ranking, and built-in summarization.

* [OCX v2.0.11](https://github.com/kdcokenny/ocx) – OpenCode extension manager providing portable, profile-based configs, isolated registries, and SHA-256-verified, version-pinned components.

* [Thunderbolt v0.1.96](https://github.com/thunderbird/thunderbolt) – Cross-platform AI client for on-prem and local models with enterprise features and self-hosting support.

* [VICE v3.2.1](https://github.com/Webba-Creative-Technologies/vice) – Security auditing CLI for web applications supporting remote black-box scans and local white-box code audits.

* [OpenSwarm v0.4.4](https://github.com/unohee/OpenSwarm) – Autonomous orchestrator that runs Claude Code agents to process Linear issues, produce code changes, report to Discord, and store memory in LanceDB embeddings.

* [Stacklit v0.4.0](https://github.com/glincker/stacklit) – Command-line tool that generates a compact codebase index and visual map for AI agents.

* [Hivemind v0.7.71](https://github.com/activeloopai/hivemind) – Persistent cloud-backed shared memory for Claude Code, OpenClaw, and Codex agents.

* [AgentOS v0.9.34](https://github.com/framerslab/agentos) – TypeScript framework for AI agents with persistent cognitive memory, runtime tool forging, and multi-agent orchestration.

* [snow-ai v0.7.35](https://github.com/MayDay-wpf/snow-cli) – AI-powered command-line interface for developer workflows, code assistance, and prompt management.

* [OpenGUI v0.5.19](https://github.com/akemmanuel/OpenGUI) – Desktop and web command center for coding agents with multi-project sessions, streaming chat, prompt queue, model switching, and voice input.

* [tmax v1.9.3](https://github.com/InbarR/tmax) – Cross-platform multi-terminal app with tiling layouts, floating panels, and keyboard-driven workflow.

* [Happier ui-desktop-dev](https://github.com/happier-dev/happier) – End-to-end encrypted mobile, web, and desktop companion for running and continuing local AI coding agent sessions.

* [Guaardvark v2.5.4](https://github.com/guaardvark/guaardvark) – Self-hosted AI workstation providing autonomous screen agents, multi-tier neural routing, media generation, upscaling, RAG, voice interface, and local tool execution.

* [IJFW (It Just F*cking Works!) v1.5.6](https://github.com/FerroxLabs/ijfw) – Local-first infrastructure for multiple AI coding agents with shared memory, smart routing, multi-AI audits, and disciplined workflows.

* [Adaline Gateway v1.11.23](https://github.com/adaline/gateway) – Fully local, production-ready SDK that provides a unified interface for calling over 300 LLMs with batching, caching, and extensibility.

* [Sendmux Feedback Widget v0.1.3](https://github.com/Sendmux/website-feedback-widget) – Drop-in accessible web component that collects feedback and sends JSON to webhooks or a server-side relay.

* [Late v1.2.6](https://github.com/mlhher/late-cli) – Deterministic coding agent orchestrator that spawns ephemeral subagents to perform exact-match code edits and avoid context bloat.

* [maestro v0.106.1](https://github.com/ReinaMacCredy/maestro) – Local-first conductor that coordinates multi-agent software engineering via a single CLI and on-disk shared state.

* [Hazmat v0.8.1](https://github.com/dredozubov/hazmat) – macOS containment for autonomous AI coding agents, providing user isolation, kernel sandboxing, network controls, DNS blocklists, and snapshot rollback.

* [lazyagent v0.5.2](https://github.com/chojs23/lazyagent) – Terminal TUI for observing AI coding agents, sessions, subagents, tools, prompts, and token usage.

* [Kubernetes MCP Server v1.0.25](https://github.com/reza-gholizade/k8s-mcp-server) – MCP-based server exposing a standardized API for discovering, listing, managing, and monitoring Kubernetes resources.

* [Mainline v0.4.8](https://github.com/mainline-org/mainline) – Provides a Git-native memory layer that records and exposes engineering intent for coding agents before diffs.

* [SDL-MCP v0.11.4](https://github.com/GlitterKill/sdl-mcp) – Cards-first context system indexing symbols to provide compact, high-signal code context for AI coding agents.

* [ClawMem v0.10.7](https://github.com/yoloshii/ClawMem) – On-device context engine providing retrieval-augmented memory, hooks, and an MCP server for Claude Code, OpenClaw, and Hermes agents.

* [cymbal v0.13.5](https://github.com/1broseidon/cymbal) – Language-agnostic code indexer and symbol navigator built on tree-sitter for instant symbol search, cross-references, and impact analysis from the CLI.

* [Claude Agent SDK for Go v0.6.19](https://github.com/severity1/claude-agent-sdk-go) – Go SDK for integrating with Claude Code CLI, providing query and client APIs, session management, and built-in tool integrations.

* [Agentfiles 0.7.4](https://github.com/Railly/agentfiles) – Obsidian plugin to browse, create, and manage agent skills across 13+ coding assistants.

* [Beehive v0.1.109](https://github.com/storozhenko98/beehive) – Orchestrate coding agents and persistent terminals across isolated git workspaces and branches.

* [cli-agent-lint v0.3.5](https://github.com/Camil-H/cli-agent-lint) – Audits command-line tools for AI agent compatibility using 34 checks across five categories and outputs a letter-grade scorecard.

* [GAIA UI v0.3.4](https://github.com/theexperiencecompany/gaia-ui) – Collection of production-ready UI components for building conversational interfaces and AI assistants.

* [Hector v1.41.2](https://github.com/verikod/hector) – AI agent runtime for self-hosted, config-driven deployments with single-binary distribution and SQL-backed durability.

* [Claude Pets v0.1.1](https://github.com/alvinunreal/claude-pets) – Claude Code activity-based hooks that update OpenPets desktop pet states automatically.

* [20x v0.0.90](https://github.com/peakflo/20x) – Desktop app turning task lists into AI-powered agents that triage, execute, and manage tasks locally.

* [OpenClaw Dashboard v2026.6.1](https://github.com/mudrii/openclaw-dashboard) – Zero-dependency local command center for monitoring AI agent gateways, costs, sessions, cron jobs, and model usage.

* [Ouijit v1.0.51](https://github.com/ouijit/ouijit) – Git worktree-based task and terminal session manager integrating agent CLIs, lifecycle hooks, and VM sandboxing.

* [Genie v4.260531.1](https://github.com/automagik-dev/genie) – CLI that interviews you, builds a plan, runs parallel agents in isolated worktrees, and outputs reviewed pull requests.

* [Mister Morph v0.2.86](https://github.com/quailyquaily/mistermorph) – Unified agent CLI and reusable Go agent core.

* [AG-UI release/2026-05-29](https://github.com/ag-ui-protocol/ag-ui) – Lightweight event-based protocol standardizing AI agent integration with user-facing applications.

* [HackerAI desktop-v0.0.54](https://github.com/hackerai-tech/hackerai) – AI-powered penetration testing assistant providing automated reconnaissance, exploit guidance, and reporting.

* [holaOS holaOS-2026.528.1](https://github.com/holaboss-ai/holaOS) – Agent environment for long-horizon work, continuity, and self-evolution.

* [MIRA (A Persistent Entity) v2026.05.01](https://github.com/taylorsatula/mira-OSS) – Persistent, self-directed conversational agent with decaying long-term memory, auto-configuring tools, and collaborative longform document support.

* [OpenACP v2026.518.2](https://github.com/Open-ACP/OpenACP) – Self-hosted bridge connecting 28+ AI coding agents to Telegram, Discord, and Slack via the Agent Client Protocol.

* [Hive v0.6.0-alpha.0](https://github.com/tt-a1i/hive) – Browser-native hive-mind for CLI coding agents that lets Claude Code, Codex, Gemini, and OpenCode collaborate as PTY processes via a team protocol.

* [OpenCode Portal cli-v0.1.32](https://github.com/hosenur/portal) – Mobile-first, responsive web UI for interacting with OpenCode sessions, offering chat, session management, Git integration, and in-browser terminal.

* [E2B Infrastructure 2026.19](https://github.com/e2b-dev/infra) – Infrastructure supporting AI code interpreting platform deployment and management.

* [OpenCove v0.2.0-nightly.20260...](https://github.com/DeadWaveWave/opencove) – Infinite 2D canvas workspace that organizes AI agents, terminals, tasks, and notes.

* [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.

* [_mom_ v0.40.0-alpha](https://github.com/momhq/mom) – Local-first persistent memory layer for AI coding agents, storing decisions and tool transcripts for recall across sessions and tools.