* [Claude-Mem v13.16.0](https://github.com/thedotmack/claude-mem) – Persistent memory compression system that preserves and summarizes context across Claude Code sessions for continuity.

* [caveman v2.2.0](https://github.com/JuliusBrussee/caveman) – Claude Code skill compressing agent output into telegraphic, technical phrasing to cut output tokens about 65% while preserving accuracy.

* [Open Design open-design-v0.21.0](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.

* [Career-Ops web-v0.8.0](https://github.com/santifer/career-ops) – AI-powered job search pipeline that evaluates offers, generates tailored ATS PDFs, scans portals, and tracks applications.

* [dyad v1.12.0](https://github.com/dyad-sh/dyad) – Local AI app builder focused on privacy, speed, and user control with support for custom API keys.

* [OpenWhispr v1.9.0](https://github.com/OpenWhispr/openwhispr) – Desktop dictation application converting speech to text with local and cloud model support and privacy-first design.

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

* [Meridian meridian-v1.63.0](https://github.com/rynfar/meridian) – Local Anthropic API proxy routing requests to Claude Max via the official Claude Code SDK.

* [OmniRoute v3.8.50](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.

* [CodePilot v0.67.10](https://github.com/op7418/CodePilot) – Native desktop GUI for Claude Code enabling conversational coding, project-aware sessions, and file-tree management.

* [Headroom v0.9.0](https://github.com/gglucass/headroom-desktop) – Local-first desktop tray app that routes coding clients through a token-saving optimization pipeline and shows savings analytics, primarily for Claude Code.

* [Claude Platform CLI v1.27.0](https://github.com/anthropics/anthropic-cli) – Command-line tool for interacting with the Claude Developer Platform API, sending messages and managing resources.

* [Simulator.Company Claude Code & Codex Plugin v2.8.0](https://github.com/corezoid/simulator-ai-plugin) – MCP-based Claude Code and Codex plugin that exposes Simulator.Company REST APIs and domain skills for managing actors, graphs, forms, and finance workflows.

* [LoongPort v6.8.0](https://github.com/SailingLoong/LoongPort) – LoongPort provides an API key and base\_url configuration helper for cc-switch relay providers, using a local SQLite store and a Tauri-based CLI.

* [agentglass v0.12.0](https://github.com/SirAllap/agentglass) – Mission-Control style dashboard and workspace that monitors AI coding agent activity in real time, with cost tracking, diffs, terminal, and source-control controls.

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

* [Raven v2.4.0](https://github.com/Laxcorp-Research/project-raven) – Local desktop meeting copilot providing real-time dual-stream transcription, WebRTC AEC3 echo cancellation, and context-aware Claude or OpenAI assistance.

* [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.

* [OmniAI v3.8.0](https://github.com/ksylvest/omniai) – Unified Ruby API for integrating with multiple AI providers, streamlining development with a consistent interface.

* [Zero v0.8.0](https://github.com/Gitlawb/zero) – Terminal-based AI coding agent that inspects repositories, edits files, runs commands, and manages local sandboxed sessions with configurable model and permissions.

* [opencode-with-claude v1.9.0](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.

* [ccLoad v4.7.0](https://github.com/caidaoli/ccLoad) – Go-based API server integrating Claude, Codex, Gemini and OpenAI models with Gin, DB support and Docker deployment.

* [DBHub v1.2.1](https://github.com/bytebase/dbhub) – Zero-dependency MCP server that provides safe, token-efficient read-only database access across PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite.

* [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.

* [Better Agent Terminal v3.2.4](https://github.com/tony1223/better-agent-terminal) – Cross-platform terminal aggregator with multi-workspace management and built-in Claude Code agent integration

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

* [PasteGuard v0.9.3](https://github.com/sgasser/pasteguard) – OpenAI-compatible privacy proxy that masks personal data and secrets before they reach external LLMs.

* [scrollcraft nateherk-design--v0....](https://github.com/nateherkai/scroll-craft) – A Claude Code skill that generates premium scroll-driven websites by enforcing unique page grammars, engineered interaction, typography, and measured scroll-craft checks.

* [liter-llm v1.18.1](https://github.com/xberg-io/liter-llm) – A lighter, faster, safer universal LLM API client built with a Rust core and many native language bindings, with a drop-in OpenAI-compatible proxy.

* [WhereMyTokens v1.24.3](https://github.com/jeongwookie/WhereMyTokens) – Local-first Windows tray app for monitoring Claude Code, Codex, and Antigravity token usage, costs, sessions, rate limits, and related efficiency and activity metrics.

* [CliRelay v0.4.29](https://github.com/kittors/CliRelay) – Unified proxy server that routes AI CLI tool requests to multiple provider endpoints with authentication, load balancing, failover, and logging.

* [dario v5.5.73](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.

* [claude-desktop-extra v1.37937.0](https://github.com/patrickjaja/claude-desktop-extra) – Unofficial repackaging of Anthropic’s Claude Desktop for Linux distros, adding Computer Use, custom themes, multiple profiles, quick entry, and a Linux hardware feature.

* [sx v2.3.7](https://github.com/sleuth-io/sx) – Package manager for team-shared AI assets including skills, MCP configs, commands, and scoped installs.

* [Oh My OpenCode v5.0.0-beta.19](https://github.com/code-yeongyu/oh-my-openagent) – Agent harness that orchestrates diverse models for automated coding, reasoning, and task execution.

* [ClawRouter v0.12.246](https://github.com/BlockRunAI/ClawRouter) – Smart LLM router that locally routes requests to the cheapest capable model across 30+ providers, reducing inference costs.

* [GoModel v0.1.80](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.

* [Hivemind v0.7.148](https://github.com/activeloopai/hivemind) – Persistent cloud-backed shared memory for Claude Code, OpenClaw, and Codex agents.

* [Rove v0.8.195](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.

* [GoClaw v3.15.0-beta.197](https://github.com/nextlevelbuilder/goclaw) – Multi-agent AI gateway connecting LLMs to tools, channels, and data with team orchestration and multi-tenant PostgreSQL.

* [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.