An auth proxy for accessing remote MCP servers using Google Cloud Application Default Credentials (ADC)
Token-budgeted, drift-aware MCP memory engine for AI coding agents: strict 25-word facts, SQLite WAL with BM25 search, Git push webhook drift detection, and multi-client synchronization.
Result-integration boundary over @modelcontextprotocol/sdk: connect to MCP servers, discover tools, and adapt them into @fgv/ts-extras ai-assist client tools
Your AI agents stop repeating the same tool mistakes. No rules to write – it learns by itself.
OpenTelemetry instrumentation for GenAI applications on Node.js, in browsers and in React Native (port of genai_otel_instrument)
Connect Claude Code, Cursor and Codex to Mirrorly, where people and their agents write docs together, live, over MCP: npx mirrorly install
Publishing from Krowk, the coding agent harness, for any MCP client: an MCP server that turns an agent's screenshots, recordings, diffs and logs into links that unfurl in Slack and Basecamp; in GitHub
The cairn command: link projects to a shared memory and wire Agent Cairn into Claude Code.
Clerk OAuth access-token authorization for Toolgrain MCP servers.
EU AI Act compliance: scan, attest, document — from your IDE. Source-available, MCP-native, AI-assisted.
Official TypeScript client for NoneCap, the hCaptcha solver API.
Local long-term memory for terminal coding agents: blueprints, code anchors and distilled lessons in one JSON file, restoring project context across sessions.
Self-hosted project-continuity hub for coding agents: tracks unfinished work, progress, overlap and reminders across clients.
Agent Cairn server: MCP endpoint, JSON API and dashboard for shared agent memory.
Detect stale references and context rot in AGENTS.md files. Keep your AI coding agents accurate and cost-efficient.
FIDES TypeScript SDK: create and verify FIDES, build, simulate and execute agent workflows.
MCP server exposing BaseNative validation, SSR preview, and directive reference to any agent
Model Context Protocol (MCP) server for the Inio REST API: read customers, invoices, pauses and retry attempts from any AI assistant
Clerk authentication integration for xmcp
RushDB SDK for JavaScript and TypeScript: the client for RushDB, the database for AI (RushDB Cloud or self-hosted)
Workspace-aware BaseMind MCP bridge for DeepSeek Harness: every session gets BaseMind's code-intelligence tools for the repository it works in, with no MCP row to configure.
ATS resume checker MCP server: lets Claude, Cursor or VS Code read your resume the way an applicant tracking system does and score it with a published, deterministic rubric. Runs locally.
GitHub MCP proxy server — bridges the official @modelcontextprotocol/server-github with Alfe OAuth credentials (Pattern A multi-account)
Record the decisions your AI coding agent makes, right next to the code.
Local-first shared memory and coordination for coding agents on PostgreSQL/pgvector: repository evidence, reservations, handoffs and code graph context.
Installer for the TRTC Agent Skills suite (Chat, Call, RTC Engine, Live, Conference) plus manual SDK runtime log troubleshooting and knowledge base, with one-command MCP setup for Claude Code / Cursor
A free desktop CLI that automatically creates mocks and tests from watching your app run.
Local-first memory for coding agents: stores facts, decisions, patterns and architecture notes in SQLite to reduce repeated context across sessions.
Persistent fractal graph memory for coding agents: semantic search, hot/cold/archive context tiers and decision tracking on Qdrant.
Automated ADR (Architecture Decision Records) for AI Coding Agents - MCP server with SQL-backed decision repository
Gmail, Calendar, Drive, Sheets, Tasks and Contacts for agents, with your own Google login
Local memory for coding agents where rules with machine-checkable proofs block matching commands, plus an append-only event log and per-project scoping.
Persistent codebase knowledge for coding agents: symbols, dependency graphs, co-change patterns and architectural decisions extracted with tree-sitter.
Persistent memory for coding agents storing architecture decisions, bug root causes and conventions, with full-text search and token-budgeted context assembly.
Local-first memory CLI for coding agents: SQLite-backed context, graph-aware recall via FTS5 and RRF, and governed memory with promote and review gates.
Local-first memory for coding agents that turns coding sessions into reusable engineering memory: decisions, gotchas and domain knowledge.
Toàn bộ thư mục
IDE, git, lint và phân tích mã. 8,724 máy chủ, dùng nhiều nhất xếp trước. Mỗi máy chủ mở ra trang của nhà phát hành.