ChannelTerm is an open-source MCP server that enables humans and AI agents to share live serial and SSH terminal sessions for embedded systems development and debugging. It allows AI agents to read device output, execute commands, assist with GDB debugging, and transfer files while keeping developers in control.

Self-hosted work log your team's AI agents write: daily updates drafted from git and the session, tasks, time measured from agent sessions, project context and client access. 39 tools over Streamable HTTP, with personal keys for coding agents and OAuth for the Claude and ChatGPT apps.

Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..

An MCP server that lets AI agents automate Microsoft Edge, organizing sessions into labelled tab-group workspaces or separate profiles and providing tools for browser control, screenshots, extraction, and secure sign-in through Edge's password manager.

Open-source Claude Code plugin porting the internal /skillify skill: turn a finished session's repeatable workflow into a reusable SKILL.md you can rerun with a slash command.

A self-hosted MCP memory server that gives every MCP-compatible agent a shared, persistent memory layer, so preferences, project conventions, and past decisions carry across sessions and across different agents and vendors. It combines hybrid keyword-plus-vector retrieval with automatic context injection, zero-config sync, and selective injection of memories by agent and priority.

PTY session management, WebSocket streaming, and REST API server for Claude Code conversations

Run multiple Claude Code accounts as one. Auto-switches on rate limits and resumes your session no lost context, no logout dance.

Enables AI agents and LLMs to persist facts, preferences, and observations in a local SQLite store and to build and traverse subject-predicate-object knowledge graphs across sessions. It provides fuzzy keyword search and graph queries so assistants retain context and recall prior project history without repeating prompts.

Enables compatible assistants to inspect Live sessions, silently mix and master bounced stems, compare references, design with installed plugins, and track local evidence and progress through supported tools.

Connect Claude Duet to Claude Code: an MCP connector that lets Duet start Claude Code sessions, talk to your open terminal windows, and get answers back. Remote MCP server on Cloudflare Workers + a Claude Code channel.

Enables a single owner to run an authenticated Streamable HTTP MCP endpoint backed by their own BotFather token, with tools to check bot status, poll allowlisted updates, inspect and acknowledge pending messages, and optionally send replies when explicitly enabled. It supports safe disconnected startup and avoids private-account sessions, multi-user services, schedulers, or automatic retries.

Enables AI clients to preview, search, read, create, update, schedule, and unschedule Garmin Connect workouts using a local Garmin session, with guarded writes and a limited tool set. Supports running, cycling, cardio, and strength workouts without exposing generic API, filesystem, or shell access.

Enables searching, reading, and privately archiving news from supported publisher subscriptions, with per-user authentication via human sign-in links and separate tokens, sessions, and archives.

An MCP server that lets any MCP client run or join a governed MACP Decision session, enforcing who may propose, vote and commit, and returning a binding Commitment whose hash anyone can recompute.

Enables Claude and other MCP clients to search finn.no and create, manage, and publish Torget ads from photos — preparing images (EXIF/GPS stripping, resize, HEIC), writing titles and Norwegian descriptions, suggesting category and market price, checking for duplicates, and publishing only after explicit confirmation. Read-only search, listing details, saved-search diffs, and management of your own ads are also supported through a locally stored logged-in session.

Enables an LLM client to perform reverse engineering inside IDA Pro without the GUI, opening databases headlessly in persistent worker processes and exposing tools to decompile and disassemble functions, rename symbols, retype variables and arguments, add comments, and convert numeric bases. It can also run over stdio or HTTP transports and adopt an existing GUI session when desired.

Enables Codex sessions to observe and control the Windows desktop through screenshot reasoning, archived-frame inspection, pixel sampling, keyboard/mouse input, and workspace-local multimodal memory.

Enables any MCP-compatible client to persist long-term memories for AI agents, with LLM-based fact extraction, semantic vector search, update/delete/list operations, and queue status checks across sessions.

Enables Claude Code and Codex to write, update, and retrieve durable long-term memories that survive session boundaries and context compaction. All recall runs locally against a single SQLite file using hybrid BM25, embedding, and recency ranking cut to an explicit token budget, with no cloud dependency.

Enables AI coding agents to automatically compress context at agent-judged task boundaries, write incremental structured session snapshots, and maintain per-fact long-term memory for priority restoration across sessions.

Self-hosted daemon connecting Claude Code, Codex, and other coding agents across machines via MCP + A2A: delegate tasks, ask questions, share results, and wake sessions.

Connects MCP hosts and LangChain agents to a local WAHA (WhatsApp HTTP API) instance, exposing tools for session management, chats, messages, contacts, and sending text, images, or files. It also provides an operational skill prompt covering lifecycle, chat ID formats, send guardrails, media rules, and error handling.

Enables LangChain ReAct and deep agents to manage WhatsApp sessions, chats, contacts, and messages—including sending text, images, and files—through MCP tools backed by a local WAHA instance.