* [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.

* [Oh My OpenCode v4.0.0](https://github.com/code-yeongyu/oh-my-openagent) – Agent harness that orchestrates diverse models for automated coding, reasoning, and task execution.

* [Frontend Slides v2.1.0](https://github.com/zarazhangrui/frontend-slides) – Claude Code skill that generates animation-rich, single-file HTML presentations and converts PowerPoint to responsive web slides.

* [dyad v1.0.0](https://github.com/dyad-sh/dyad) – Local AI app builder focused on privacy, speed, and user control with support for custom API keys.

* [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.

* [AgentSys v6.0.0](https://github.com/agent-sh/agentsys) – Modular runtime and orchestration system for composing AI agents, plugins, and skills into structured development pipelines.

* [LangChain langchain-perplexity...](https://github.com/langchain-ai/langchain) – Framework for building agents and LLM-powered applications with modular components and integrations.

* [GoClaw v3.12.0](https://github.com/nextlevelbuilder/goclaw) – Multi-agent AI gateway connecting LLMs to tools, channels, and data with team orchestration and multi-tenant PostgreSQL.

* [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.

* [Open CoDesign v0.2.0](https://github.com/OpenCoworkAI/open-codesign) – Turn prompts into polished interactive prototypes, slide decks, PDFs, and marketing assets with local, user-chosen models.

* [Claude Cowork on Linux v5.0.0](https://github.com/johnzfitch/claude-cowork-linux) – Run Claude Desktop's Cowork local-agent mode natively on Linux without macOS or a VM, using reverse-engineered stubs for macOS native modules.

* [RubyLLM 1.15.0](https://github.com/crmne/ruby_llm) – A Ruby library providing a unified API for interacting with various AI models and services.

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

* [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.

* [claude-code-cache-fix v3.8.0](https://github.com/cnighswonger/claude-code-cache-fix) – Fixes prompt-cache regressions in Claude Code that can increase resumed-session costs up to 20x and adds monitoring for context degradation.

* [Claude Code on Android v2.9.0](https://github.com/ferrumclaudepilgrim/claude-code-android) – Run Anthropic's terminal-based AI coding assistant on Android via Termux, proot, or AVF without root or emulation.

* [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.

* [Claude Platform CLI v1.10.0](https://github.com/anthropics/anthropic-cli) – Command-line tool for interacting with the Claude Developer Platform API, sending messages and managing resources.

* [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.

* [AZMX AI v0.26.0](https://github.com/AzmxAI/azmx) – Sovereign agent platform for local or bring-your-own models, with per-call approvals and tamper-evident audit logs.

* [Better Agent Terminal v3.1.0](https://github.com/tony1223/better-agent-terminal) – Cross-platform terminal aggregator with multi-workspace management and built-in Claude Code agent integration

* [AI Context v1.16.0](https://github.com/Tanq16/ai-context) – CLI that generates AI-friendly Markdown context from local repos, GitHub, YouTube, or webpages.

* [storybloq v1.4.0](https://github.com/Storybloq/storybloq) – Cross-session context persistence for AI coding using a .story directory, CLI, MCP server, and Claude Code/Codex skill.

* [Open Cowork v3.3.1](https://github.com/OpenCoworkAI/open-cowork) – Personal AI agent desktop app with one-click Windows/macOS installers, sandboxed workspace, extendable skills, and remote GUI automation.

* [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.

* [SeekerClaw v2.0.0](https://github.com/sepivip/SeekerClaw) – On-device Android AI agent running 24/7 via Node.js, controllable through Telegram, with device control and Solana wallet integration.

* [dario v4.7.0](https://github.com/askalf/dario) – Local LLM router exposing one endpoint to proxy Anthropic and OpenAI-compatible providers, enabling tools to use Claude subscriptions and other backends.

* [AIPointer v1.1.0](https://github.com/talentsache/aipointer) – Cursor-anchored vision LLM overlay that answers questions about the area under your pointer with multi-provider and voice support.

* [AIPointer v1.1.0](https://github.com/gonemedia/aipointer) – Cursor-anchored desktop overlay that captures a screen region and queries vision-capable LLMs for contextual answers.

* [Career-Ops career-ops-v1.8.0](https://github.com/santifer/career-ops) – AI-powered job search pipeline that evaluates offers, generates tailored ATS PDFs, scans portals, and tracks applications.

* [caveman v1.8.2](https://github.com/JuliusBrussee/caveman) – Claude Code skill compressing agent output into telegraphic, technical phrasing to cut output tokens about 65% while preserving accuracy.

* [tweakcc v4.0.13](https://github.com/Piebald-AI/tweakcc) – CLI tool for customizing Claude Code prompts, themes, toolsets, UI, and behavior across native and npm installations.

* [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.

* [go-anthropic v2.20.0](https://github.com/liushuangls/go-anthropic) – Anthropic Claude API wrapper for Go supporting completions, streaming, messages, vision, tools, and token counting.

* [Vellum Assistant v0.8.0](https://github.com/vellum-ai/vellum-assistant) – Personal AI assistant that learns your preferences, maintains structured memory, acts proactively, and enforces strict trust and sandboxed tools.

* [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.

* [cc-clip v0.8.0](https://github.com/ShunmeiCho/cc-clip) – Clipboard and notification bridge enabling image paste and notifications over SSH from macOS/Windows to remote Claude Code or Codex CLI.

* [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.

* [Meridian meridian-v1.43.0](https://github.com/rynfar/meridian) – Local Anthropic API proxy routing requests to Claude Max via the official Claude Code SDK.

* [MCP SSH Manager v3.5.1](https://github.com/bvisible/mcp-ssh-manager) – MCP server that lets AI assistants manage SSH connections, run commands, transfer files, handle backups, databases, and monitor server health.

* [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.

* [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.

* [claude-view v0.41.0](https://github.com/tombelieber/claude-view) – Live dashboard to monitor Claude Code sessions with real-time status, cost tracking, search, and sub-agent visibility.

* [OpenStudy v0.7.0](https://github.com/OpenStudy-dev/OpenStudy) – Self-hostable personal study dashboard that tracks courses, schedules, lectures, deliverables, and tasks with MCP/Claude integration.

* [Arkloop v26.5.15](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.

* [opencode-claude-auth v1.5.4](https://github.com/griffinmartin/opencode-claude-auth) – Self-contained Anthropic auth provider for OpenCode using Claude Code credentials, no separate login or API key needed.

* [AICommit2 v2.5.19](https://github.com/tak-bro/aicommit2) – Reactive CLI generating commit messages for Git, YADM, and Jujutsu using Ollama, ChatGPT, Gemini, Claude, Mistral, and other AI providers.

* [opencode-with-claude v1.6.11](https://github.com/ianjwhite99/opencode-with-claude) – OpenCode plugin that starts a local Claude Max proxy when OpenCode launches and manages its lifecycle and session headers.

* [Vurb.ts v3.19.5](https://github.com/vinkius-labs/vurb.ts) – TypeScript framework for building MCP servers with type-safe APIs, machine-readable SKILL.md, AI-agent integration, and built-in security.

* [Claude Desktop for Linux v1.10628.0](https://github.com/patrickjaja/claude-desktop-bin) – Unofficial Linux packages for a desktop AI assistant with automated updates and multi-distro installers.

* [Hivemind v0.7.70](https://github.com/activeloopai/hivemind) – Persistent cloud-backed shared memory for Claude Code, OpenClaw, and Codex agents.

* [GoModel v0.1.35](https://github.com/ENTERPILOT/GoModel) – High-performance Go-based AI gateway providing an OpenAI-compatible API and unified access to multiple LLM providers with observability, guardrails, and streaming.

* [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.

* [CliGate v1.2.2](https://github.com/codeking-ai/cligate) – Multi-protocol local AI gateway routing pooled accounts and API keys for Claude Code, Codex CLI, Gemini CLI, and OpenClaw with a visual dashboard.

* [VoidLLM v0.0.19](https://github.com/voidmind-io/voidllm) – Privacy-first LLM proxy and AI gateway offering multi-provider routing, API key management, usage tracking, rate limiting, and load balancing.

* [ChatBotKit Node SDK @chatbotkit/react@1....](https://github.com/chatbotkit/node-sdk) – JavaScript-based platform for building conversational AI bots and agents.

* [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.

* [claude-cowork-service v1.0.57](https://github.com/patrickjaja/claude-cowork-service) – Native Linux backend for Claude Desktop's Cowork feature that implements its JSON-over-Unix-socket protocol and runs commands natively instead of via a VM.

* [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.

* [NodeTool v0.7.1-nightly.20260...](https://github.com/nodetool-ai/nodetool) – Visual platform for building and deploying AI workflows, agents, and multimodal pipelines via drag-and-drop nodes.

* [liter-llm v1.4.0-rc.48](https://github.com/kreuzberg-dev/liter-llm) – Universal LLM API client with a Rust core, 11 native language bindings, and support for 143 providers.