Production-ready AI agent profiles for Claude Code, Cursor, Codex, OpenClaw, and Hermes. Search, install, and contribute ForgeCat packages.

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.

Enables AI agents to drive a real Chromium browser by receiving compact, token-efficient page maps and only the changes after each action. It guards against hidden prompt injections, blocks payments, sends and deletions until the user approves, and lets agents learn site-specific notes over time.

Enables agents to bring claims, situations, and Scripture passages to five doors (Check, Find, Walk, Word, Keep) and receive a verdict, the worked reasoning trail, cited sources, and a re-checkable content-addressed seal. It covers 77 verifier domains and 880k+ cards fully offline, so answers are found, verified, and sealed rather than generated.

Best ready-to-run DeepSeek Harness distribution: DSH desktop GUI, DSH terminal TUI, and harness integration.

Enables agents to query real-time GPU rental prices across 26 platforms, including current lowest quotes, 30-day price history, market movers, platform reliability, and task/budget recommendations. Access is read-only and metered per call via x402 with USDC on Base, requiring no signup or API key.

A hosted remote MCP server that gives AI agents live hotel, Airbnb/Vrbo and flight pricing tools — nightly rate calendars up to 330 nights, every booking site's price for a stay compared against the hotel's own site, guest reviews, and Google Flights search. Clients connect over Streamable HTTP with browser OAuth or an API key, so nothing needs to be installed or run locally.

Gives browser agents a reviewed map of 79 real sites — entry URLs, access verdicts, and role/accessible-name button maps for 104 screens — so an agent can find where things are and know whether it may act at all. Safety rules in code halt irreversible actions such as pay, order, submit and delete pending explicit human approval, while per-site memory recalls which routes worked last time.

Enables an AI agent to drive a remote Linux machine over the LAN through a single TCP connection, exposing tools for shell commands, jobs, interactive PTYs, file read/write/search/transfer, process and service management, networking, packages, and power control, with optional multi-host switching. Operates without SSH or any Linux-side installation beyond one stdlib-only Python daemon, using a state-free binary protocol.

Enables a single owner to run a self-hosted authenticated MCP server that adds Slack reading and replying, Outlook inbox and calendar lookup, signed Slack event capture, restricted KakaoTalk Windows-agent tasks, appointment tracking, and morning briefings to an existing MCP setup.

Enables an agent to verify its own work mid-task by deliberately breaking each changed line, re-running the test suite in isolated workers, and reporting which breaks no test catches, along with a plan tool that previews which changed lines would be checked.

Turns any OpenAPI 3.x spec into an MCP server that exposes one validated tool per API operation, so AI agents can discover and call a REST API over stdio or Streamable HTTP. It is read-only by default, with allow/deny lists, environment-based auth, timeouts and response truncation for safe agent access.

Enables an AI agent to see and control the screen of an already-running macOS virtual machine over VNC, exposing four tools: screenshot, click, type_text, and key_press. This lets the agent drive a disposable VM's UI directly with its own model, without touching the real desktop or running a separate agent loop.

Enables MCP clients to query and diagnose machine-learning training runs through read-only tools for listing experiments, reading configurations and final metrics, comparing runs, sampling metric curves, and detecting training failures.

Enables AI agents to write, compose, and check assume-guarantee contracts, including refinement, consistency, compatibility, realizability, and LTL checks, and to use returned counterexamples to fix specifications.

Enables read-only monitoring and diagnostics of Apache Flink clusters through a JobManager REST endpoint, including job, checkpoint, backpressure, TaskManager, and multi-cluster overviews with LLM-friendly summaries.

Enables learners to browse, read, and be quizzed on saved lessons inside Claude Desktop and Claude Code, and enables five Claude agents to build fact-checked K–College lessons through guarded, pinned MCP tools.

Enables MCP agents to take a break after repeated failures, receive encouragement and a concrete next step, and report outcomes to track recovery.

Provides OAuth-secured MCP tools for working with private, Git-backed Markdown knowledge bases: searching pages, reading content, ingesting new source documents, retrieving cited original files, and reviewing history or rolling back accepted pages. Every tool call is checked against each person's or agent's current wiki grant and returns source paths and Git revisions for traceability.

Exposes MCP tools that compute longevity and metabolic metrics (autophagy index, GKI, MAGE), cardio-renal biomarkers (BUN/creatinine ratio, cardiac output and TPR, nocturnal BP dipping), chronobiology estimates (DLMO, melanopic lux, caffeine clearance), plus neuro-recovery and biomechanics scores. Runs as a zero-dependency Python JSON-RPC 2.0 stdio server so any MCP-compatible client can query these physiological domain calculators.

Enables AI agents to browse and manage a gThumb image library by reading and writing catalogs, tags, ratings, comments, thumbnails, and search results directly in gThumb’s own data.

Gives AI agents read-only access to curated, deduplicated, and well-described data products, complete with source metadata, freshness tracking, and per-agent permissions that preserve the source's access rights. The server can also answer "I don't know" rather than guessing when the approved data doesn't cover a question.

Exposes four read-only tools over extracted Hacker News "Who is hiring?" job posts — postings_search, posting_get, skills_top, and skills_trend — so an MCP client or agent can search postings, look up individual posts, rank top skills, or chart skill trends over time. Tools return only structured extracted fields and HN links (never raw post text) from a read-only SQLite database, including salary sorting and a hard row limit to keep queries cheap.

Enables AI coding agents to query a locally indexed codebase graph for symbol definitions, immediate callers and callees, and multi-hop downstream dependency impact analysis through MCP tools.