JSPM

AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory. Branch a base memory in ~0.5ms / 162 bytes regardless of base size — 83x faster, 3000x smaller than full-copy snapshots. Exact read-through queries (parent ∪ edits, chil

Claudeflow — AI-powered development toolkit for Claude Code and Codex. Skills, agents, hooks, and quality gates that ship production apps.

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

TypeScript SDK for Agent Relay — WebSocket bus client, HTTP client, and shared types

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Standalone swarm coordination - up to 100+ agents, 4 topologies, hive-mind, consensus

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

TypeScript SDK for Loki Mode - autonomous multi-agent development platform

A Unified Virtual Filesystem For AI Agents

Loki Mode by Autonomi. Autonomous spec-to-product system: takes a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief to a deployed app via the RARV-C closure loop with 8 quality gates. Provider-agnostic (Claude Code, OpenAI Codex, Cline, Aider).

A Unified Virtual Filesystem For AI Agents

Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo

Project memory and workflow context for AI coding agents.

Run Claude Code and Codex CLI as local background agents that message each other, wake on demand, and share one memory.

Claude-Code-style dynamic workflows for Pi — fan a task out across 100s of subagents with real model routing, token/cost accounting, resume, git-worktree isolation, an interactive /workflows TUI, and a real /deep-research.

D2 export adapter for DiagramPilot.

Private on-chain communication for autonomous agents. ECIES-encrypted messaging on any EVM chain.

AI employee operating system — persistent memory, task management, and multi-agent coordination for Claude Code.

Universal AI Development Platform with working MCP integration, multi-provider support, voice (TTS/STT/realtime), and professional CLI. 58+ external MCP servers discoverable, multimodal file processing, RAG pipelines. Build, test, and deploy AI applicatio

The Hashgraph Online Standards SDK provides a complete implementation of the Hiero Consensus Standards (HCS), giving developers all the tools needed to build wonderful decentralized applications on the Hashgraph network. https://hol.org

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Agentic Quality Engineering V3 - Domain-Driven Design Architecture with 13 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 60 specialized QE agents, mathematical Coherence verification, deep Claude Flow integration

One command install for the great_cto Claude Code plugin. Auto-detects your stack, picks the right archetype, bootstraps PROJECT.md.

Packaged icon metadata for DiagramPilot.

Typed TypeScript client for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.

SVG rendering and PNG rasterization adapter for DiagramPilot.

MCP server for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

DiagramSpec types and core behavior for DiagramPilot.

CLI for Tangle Sandbox operations

AgentOS: open-source TypeScript framework for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipeline, and 11 LLM providers.

Mermaid export adapter for DiagramPilot.

Unified AI coding assistant CLI - Manage Claude Code, Gemini & custom agents. Multi-provider support (OpenAI, Azure, LiteLLM, SSO). Built-in LangGraph agent with file operations & git integration.

MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati

Filesystem-first framework for durable backend AI agents that run anywhere.

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Profile your project and gear up your coding agent with the right MCP servers, skills, and hooks. Claude Code, Codex, Cursor, opencode, Gemini CLI & OpenClaw. A recommender + installer, not a list you read.

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Private virtual LAN for self-hosted services and AI agents, built on Elastos Carrier. NAT-traversal, name service, ACL, all over a peer-to-peer mesh — no public IP required.

WorkOS Skills for AI coding agents — AuthKit, SSO, Directory Sync, RBAC, and more

Workflow control for AI coding agents

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

React hooks for Model Context Protocol (MCP) - expose React components as AI tools for Claude, ChatGPT, Cursor, and Copilot with Zod validation

MoltBridge SDK — Professional network intelligence for AI agents

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Local-first identity, memory, and secrets for AI agents

411 professional Agent Skills (SKILL.md) + subagents + slash commands for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes. It's a CLI, not a library: run `npx pm-claude-skills add --agent <tool>` to install into your AI tool — no `npm install` needed. Or

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

DiagramPilot command line interface.

Fine-tune cheap open-source LLMs (GLM, Qwen, DeepSeek) on your AI coding agent's successful runs with LoRA (SFT + DPO) so your model cascade escalates to expensive frontier models (GPT, Claude) less often — cutting cost-per-resolved. Turns run history int

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

skill-map reference implementation: kernel + CLI + adapters.

OpenCode Goal Mode 0.9 — goal agent + server plugin: goal_set, idle evaluator, auto-continue until YES. Simple, no sidebar, no guard.

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

🚀 AI-Powered Swarm Intelligence Platform - Gamified MCP Development with 70+ Tools

Claude Code-first opinionated workflow framework: instructions, personas, skills, and SDLC workflows that govern AI coding assistants.

MCP server for Adobe Photoshop — 80 AI tools, recipe workflows, standalone web UI. Control Photoshop from Cursor, Claude, or natural language.

A typechecker for your issue tracker — every checked acceptance criterion must cite a real commit and proof, verified by `ztrack check` (and enforced on coding agents via a loop gate).

Amiko CLI — swap tokens, manage credits, bridge cross-chain, and call marketplace agents

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Model Context Protocol server for DiagramPilot.

Official Node.js SDK for OneCLI. Connect AI agents to external services via the OneCLI proxy.

Monomind - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration

Collective agent intelligence — Claude Code plugin

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Trust and payment rail for AI agents — identity, verification, escrow, settlement, and reputation.

CLI for onboarding and managing target repositories.

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Local-first cloud/SaaS usage, status, and expected billing CLI for MoneySiren.

AgentField TypeScript SDK

Monomind CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code

Portable AgentsKit runtime for chat orchestration, tools, memory, and retrieval.

The agent runner for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) — a thin wrapper over the Claude Agent SDK used by `agent.run` nodes. Supports capability **profiles** (`constrained` / `surface` / `full`), structured **decision** o

MCP server that gives AI assistants eyes and hands in the Godot editor: scene editing, input injection, deterministic game-time control, and live runtime state for agent-driven playtesting

RDC typed-agent dispatch skill suite for Claude Code - plan, build, review, overnight builds

gRPC PowerLine server for Grackle AI agent integration

Developer CLI for SMRT framework - introspection, testing, and project management

Behavioral litmus harness for MCP servers — grade a server A–F (tool-output injection, egress, sensitive-data, adversarial-input) with reproducible, content-addressed evidence. Ships a CLI and an MCP server with a run_litmus tool for AI agents.

MCP (Model Context Protocol) server for Grackle — translates MCP tool calls to ConnectRPC

Model Context Protocol server for the XRPL-Utilities portfolio: Sentinel (wallet classifier), Pulse (signal feed), Telemetry (supply + utility floor), Trust (XLS-70/80/81 directory), Vault (RWA tracker), and Flows (ETF AUM vs XRPL flow correlation). Expos

AI document generation CLI for PPTX, DOCX, XLSX, reports, and images.

Unify Claude Code, Codex, Cursor, and Gemini CLI with persistent context, governance, and multi-model debate.

Constella — run autonomous AI agent-companies locally: real claude/codex agents, Goals → Specs → Issues → Plans, local models, GitHub & Telegram, all from one cosmic control plane.

DOT export adapter for DiagramPilot.

TypeScript SDK for Zero — search, fetch, and pay for AI capabilities (x402 + MPP).

AI-powered terminal coding assistant with 10+ models, persistent agent memory, MCP servers, and semantic code search. Free tier with tool support.

OrionOps CLI — Specialized AI agents for code generation

JSON Schemas, prose contracts, and conformance suite for the skill-map specification.

Self-growing harnesses for Claude Code and Codex.

TypeScript client for the Vaara HTTP API: EU AI Act runtime evidence for MCP tool calls. Conformal risk scoring, policy gating, hash-chained tamper-evident audit, named detectors.

SettleMesh CLI + MCP server: deploy an agent-built app to a live URL with login, a managed database, usage-based billing, and end-user-pays — plus metered web search, LLMs, image/video, and a service catalog, all on one key.

MCP server for AI agents to investigate OpenTelemetry traces, metrics, and logs

Redux + Saga state management for Svelte apps — designed for AI agents. Includes runtime TypeScript source, AI skills, and reference documentation for robust, observable, high-performance state management.

LeanCTX — the Context OS for AI coding agents. One local binary that compresses, remembers, routes, and verifies every token between your code and the model. No Rust required.

A Unified Virtual Filesystem For AI Agents

Command-line interface for managing Grackle environments and agents

Agent memory on Google's Open Knowledge Format (OKF). Kage maintains your coding agents' OKF memory bundle in git and verifies every concept against your code, deterministically. The verification and freshness layer OKF leaves out. MCP server, no account,

CLI, Interactive TUI Dashboard, and MCP server for thingd — a fast object-first data engine for applications and AI agents.

Archil filesystem adapter for just-bash

React provider and client hook for the Stigmer platform SDK

Agent-native application framework and compiler for building Forge apps without a mandatory dashboard.

Pure business logic, types, schemas, and store interfaces for the Polpo AI agent orchestration platform

Slack for AI employees with a shared brain. A collaborative office where AI employees run your work 24x7.

The command-line runner for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) — a local-first, agent-in-the-loop workflow engine. Loads a project's `agentic-surfaces.config.yaml` + `workflows/*.yaml` + `agents/*.md`, runs the scheduler,

Autonomous development toolkit for AI agents - screenshots, DOM queries, console logs, and JavaScript execution via WebSocket and Chrome DevTools Protocol

Build AI agents on the Jelou platform — from your terminal or your AI editor.

Built-in skill definitions for the Zibby agent-workflow framework

The engine core for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) — workflow schema + loader, the node executor and handler registry (`task.http`, `task.transform`, `task.branch`, `task.foreach`, `task.cache-unseen`/`task.cache-mark`

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

The dashboard server for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) — an HTTP + SSE API (`/api/workflows`, `/api/run`, `/api/events`, `/api/cache`, …) plus the bundled web UI (workflow graph, live runs, agent activity, cache inspe

FRAIM CLI - Framework for Rigor-based AI Management (alias for fraim-framework)

MCP server for Q402. Gasless USDC/USDT/RLUSD/Q payments on 12 EVM chains (USDG on Robinhood Chain), Q402 Yield (gasless supply and withdraw into Aave, Lista, and Morpho lending vaults), gasless non-custodial escrow (create, fund, release, refund, dispute)

vg — local codebase intelligence CLI + MCP server for AI coding agents: deterministic code graph, drift reporting, and version-correct library docs (Apache-2.0)

Use the open IICP AI mesh from TypeScript or JavaScript without running a node

Conduit — Pay-per-call API marketplace powered by x402 payments on the Stacks blockchain

Minimal project memory and validation harness for AI coding agents.

Governance CLI for AI-native software delivery and AI coding agents. Enforces traceability: ADR → REQ → ROADMAP → kanban. Native support for Codex, Claude Code, Gemini CLI, Cursor, Copilot, Windsurf, and Amazon Q.

MCP server + CLI giving AI agents a real, stealth browser (Patchright/Playwright) — per-country identity, self-healing actions, snapshots, multi-step plans, structured extraction, CDP attach.

Extentos MCP server — deterministic tools for building Meta-glasses apps.

The hub-world for AI agent crews — orchestrate Claude Code, Codex, GLM, Kimi, DeepSeek & any OpenRouter model as live crews with a plan-aware Advisor, a Kanban/flow command center, a testing gate, and an economics brain (Scrooge).

Generated TypeScript protobuf stubs for Stigmer APIs

Open source frontend QA protocol runner for coding agents.

Dark Factory OSS CLI — multi-vendor adversarial critic orchestration (Cursor, Codex, Gemini, Grok) with min-complete-quorum aggregation and trusted-surface rebind

A full AI engineering team as plain Markdown files. 14 specialized agents for code quality, commits, reviews, security, and more — works with any agent runtime.

AI Agent Governance for TypeScript — policy enforcement, scoring, compliance, and audit for AI agents

stdio-to-HTTP MCP proxy for Grackle — bridges stdio-only MCP clients (Claude Desktop, Codex CLI, Clawpilot) to a Grackle HTTP MCP server using static API-key auth

Framework-agnostic primitives for AEO infrastructure: content negotiation, AI-bot detection, markdown response, token estimation, composition helpers.

A framework to structure, compile and distribute Architectural (ADR), Business (BDR), and Engineering (EDR) decision records contents so that AI agents and humans can reliably find and use them with hierarchical scopes and controlled rollout in the format

Portable, cross-agent memory & workflow for AI coding agents — Claude Code, Codex, Cursor, Devin Desktop. One command deploys an AGENTS.md entry point + docs/ai context with cap/archive/index enforcement into any repo.

One-command installer for the MoneySiren CLI, local web dashboard, and HUD.

Standalone agent runtime with ReAct loop for AgentsKit.

Stigmer TypeScript SDK — typed API client for all Stigmer platform resources

Process transparency for agentic work.

Less hallucinations. A command firewall for AI agents: validates every shell command before execution, so fabricated commands are denied before they run.

Ink (React for terminals) components for rendering Stigmer agent sessions in the terminal

Agent self-service API client — agents calling /agents/ endpoints

React SDK for OpenPolpo — hooks with real-time SSE updates, built on @polpo-ai/sdk

Logging and tracing layer for AgentsKit agents.

AGIRAILS SDK for the ACTP (Agent Commerce Transaction Protocol) - Unified mock + blockchain support

Local auto-resume supervisor for AI coding-agent terminals: detect Claude Code, Codex CLI, OMX, OpenCode, and managed-command limits, wake the original tmux pane, and verify recovery.

iCloud for AI Agents — cross-agent sessions, skills, memory, and vault.

Polpo SDK — typed HTTP client, SSE streaming, and reactive store for AI agent orchestration

A globally installed CLI harness for OpenAI Codex with durable ledgers, verification gates, memory, and replay-gated skills.

Companion listener for Agent Rooms. Pair a device, wire the MCP connector, and wake idle agents (Claude Code, Codex, OpenClaw, Hermes) on mentions and task assignments.

AI code review pipeline that turns agent-written PRs into merge-ready patches

AI-powered development system: 122 slash commands and 40 specialist agents that take a project from raw idea to hardened production, then run it as an autonomous loop. Runs inside Claude Code, Codex, Cursor, Windsurf, Gemini, and 10+ other AI coding tools

Agent Management actions for creating and managing AI agents in MemberJunction

Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha

Local bridge that exposes the AI coding agents installed on your machine — Claude Code (CLI), Codex (CLI), and Antigravity CLI (formerly Gemini CLI, which remains available for business/enterprise) — to the ChatPanel Chrome extension over a localhost SSE

LensMCP core — event bus, resource store, graph store, and pattern detectors.

Local-first repo-memory MCP for coding agents. Best for relationship-heavy edits: symbols, callers, dependencies, diff review, and git-pinned decisions before code changes. Start with a no-write proof receipt; use grep/ripgrep for exact strings. MIT; no A

Engagement marketplace on Base, native to the Bankr ecosystem: AI agents and communities fund quests (follows, reposts, replies, quotes, original posts); verified-X humans complete them and are paid per approved action from a non-custodial x402 escrow — i

Visualize and follow your agentic-surfaces workflows in the browser — run `npx agentic-surfaces` from your repo to open the live dashboard.

The real-world capability layer for AI agents — domains, email, deploy, media. CLI + MCP.

One MCP server for all web data. Search, scrape, crawl, proxy, and AI research in one install.

Infrastructure and protocol for multi-agent collective intelligence

Shared event and resource type definitions for LensMCP.

Question boards with rich blocks (markdown, charts, mermaid, tables, code, diffs, video, sandboxed HTML), clickable local file-links, and element-level annotations for AI coding agents (Claude Code, Codex, …): ask users structured questions, present inter

ThumbGate self-improving agent governance: thumbs-up/down turns every mistake into a prevention rule and blocks repeat patterns. 33 pre-action checks, budget enforcement, and self-protection for Claude Code, Cursor, Codex, Gemini CLI, and Amp.

Run wrud locally with one command - a local-first recorder for AI-agent sessions (tools, models, cost, insights). `npx @wrud/cli`.

Archmantic — an always-on Solution Architect: a living, grounded architecture model + diagrams for humans and AI agents (via MCP). Detects TS/JS and PHP/Laravel stacks, monorepos, API surface, and data models.

The standard framework for AI Driven Development.

Convenience alias for @trylayout/qa.

Drizzle ORM store implementations for the Polpo AI agent orchestration platform (PostgreSQL + SQLite)

MCP server for Docker — container management, health checks, auto-restart, Compose lifecycle, and log streaming for Claude, Cursor, and AI agents

FRAIM: AI Workforce Infrastructure — the organizational capability that turns AI agents into an accountable workforce, their operators into capable AI managers, and executives into leaders with clear optics on AI proficiency.

Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing

URL safety checker for AI agents. Detects phishing, malware, typosquatting before your agent visits any link. BLOCK/ALLOW verdict in one call.

CrawlForge MCP Server - Professional Model Context Protocol server with 27 web scraping, crawling, deep-research, and autonomous-extraction tools. Returns clean Markdown and structured JSON for Claude, Cursor, and any MCP client. Defaults to local Ollama

AI agent orchestration framework for TypeScript/Node.js - 32 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, OpenAI Responses, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS, Copilot, LangGrap

Point it at your coding-agent session traces (Claude Code, Codex, OpenCode, Gemini, Pi, …) and get failure-mode + efficiency findings. CLI + SDK over the @tangle-network/agent-eval analyst suite — observe live sessions, run your own analysts, redact, and

Persistent and vector memory backends for AgentsKit.

Autonomous dev pipeline for Claude Code. GitHub as institutional memory — every issue, PR, and annotation survives context resets and makes the next agent smarter.

Claude Code-native workflow distribution.

Fidacy action firewall for AI agents. Mandate-gated payment authorization as an MCP server.

Software Teams specialist agents as n8n community nodes. Self-hosted only — requires the claude binary and ANTHROPIC_API_KEY on the n8n worker.

Generic AI CLI pet runtime foundation.

Tree-sitter indexed lookups — smart code reading for AI agents

prom.codes Memory — persistent, local-first agent memory as an MCP server.

AI got your app to demo. VibeRaven gets it to production. Run `npx viberaven` for the local launch console.

Local-first flight recorder + context-efficiency profiler for coding agents — records Claude Code, OpenCode, and Gajae-Code. Run with npx.

CLI for 1Claw — secrets management for AI agents and humans

The language of AI

Terminal-first relay for paired AI coding agents (Claude + Codex), driven by structured workflows.

Dark Factory schemas — TypeScript types and JSON Schemas for darkfactory.yaml, evidence, and cycle-doc trailers

CLI build tool for vanilla web development with TypeScript.

Opper TypeScript SDK — execute functions, stream results, and build AI agents.

Canon core — shared types, REST client, SSE stream, and registration for Canon messaging

An opinionated Agent Development Kit for building custom AI agents with bring-your-own infrastructure and opt-in batteries.

Ready-made skills (prompts + behavioral instructions) for AgentsKit agents.

Minimal project memory and validation harness for AI coding agents.

🚀 Sistema de Agentes IA para Claude Code - Local por Projeto com 43 agentes especializados e mesa técnica obrigatória

AI model router for agents. Checks whether a local model can handle the task before calling cloud inference. LOCAL/CLOUD verdict saves cost on every call.

TypeScript SDK for stablecoin payments by AI agents. Japan-first, JPYC-native.

Reusable executable tools for AgentsKit agents.

The smith that forges specs into merged PRs — autonomous AI implementer + adversarial reviewer, pluggable engines, human gate on critical paths.

Core interfaces and types for the MemberJunction Agent Manager system

Generate AGENTS.md, repo metadata, and MCP context so AI coding agents can onboard quickly.

Web search for AI agents, as an MCP server — live web search, news, image search, read-any-page-as-markdown (scrape), and one-call research (search + read). The agent pays per call in USDC via x402: no API key, no signup. Powered by Superhighway.

216 个即插即用的 AI 专家角色定义 — 从前端开发到区块链安全，从小红书运营到抖音策略

Agentic persistent planning

The official TypeScript SDK for Agent Vault

Zero-config React instrumentation for LensMCP (Babel transform + flow/render runtime).

Unified dev-loop: one MCP server exposing browser control + dev-server logs on a correlated timeline. Headless (stdio) or Electron cockpit (HTTP).

Automated ADR (Architecture Decision Records) for AI Coding Agents - MCP server with SQL-backed decision repository

CLI for Invoke, execution reliability infrastructure for AI agents.

File-based Kanban engine backed by Markdown. Zero backend, AI-agent friendly.

Stdio relay and fallback MCP server for Agoragentic's hosted Triptych OS (Agent OS) Router / Marketplace. Exposes registration, search, provider preview, paid execution, and receipt-backed status tools.

Theme-aware visual primitives and render pipeline for AI-generated diagrams, figures, and presentation frames.

LensMCP CLI — install and run the MCP observability server coding agents use to see running apps.

Type-safe JavaScript dialect with runtime validation, sandboxed VM execution, and AI agent orchestration. Transpiles TypeScript to validated JS with fuel-metered execution for untrusted code.

Embeddable Temporal worker for the Stigmer AI agent platform — handles agent execution, workflow orchestration, and MCP server management

**atris** is an operating system for AI work. It turns any repo into a workspace an agent can actually operate: shared context it reads before it acts, a `plan -> do -> review` loop, durable tasks and daily logs, and verification that ends work on a real

Loop engineering substrate for coding agents — state, lossless optimization, and hook enforcement: verify-gated loops that can't lie, run away, or go broke. For Claude Code, Codex, Cursor, Gemini CLI, VS Code Copilot, and any MCP client.

Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines.

Figs CLI — publish your AI agent's state to Figs (figs.so). Run by the agent.

Provider adapters for AgentsKit.

ContextRelay: local multi-agent coding orchestration for Claude Code and Codex

Playground TypeScript SDK

Next.js App Router adapter for the Dualmark AEO framework. Drop-in proxy/middleware + route-handler factory + withDualmark() config wrapper. Same API surface as @dualmark/astro.

Promptbook: Run AI apps in plain human language across multiple models and platforms

TypeScript SDK for the MIOSA API - cloud VM desktop infrastructure for AI agents

FolderForge - the all-in-one MCP-native local development control plane for AI coding agents.

Portable, cross-agent memory substrate for AI coding agents — an AGENTS.md entry point + docs/ai context with cap/archive/index enforcement, deployable standalone or as part of the agent-workflow family. The memory layer of the agent-workflow family.

LensMCP container/memory mutation tracking (Map/Set/Array instrumentation).

MoFlo — AI agent orchestration for Claude Code. A standalone, opinionated toolkit with semantic memory, learned routing, gates, spells, and the /flo issue-execution skill.

Slack MCP without OAuth — 21 tools, session-based, local-first. Free OSS + hosted tier from $19/mo.

Full-stack x402 SDK - add paid API monetization to any endpoint. Express middleware, React hooks, Access Pass, dynamic pricing. Solana, Base, Polygon, Arbitrum, Optimism, Avalanche, SKALE.

Official elvix SDK. Drop-in React components, server helpers, and an MCP server so AI coding agents integrate elvix on the first try.

RelayRoom agent-side CLI - connect Claude Code over MCP, run the pager, install the usage hook.

Atlas by Synthetic Sciences - research map CLI and skills.

Glasstrace server-side debugging SDK for AI coding agents

MCP server for AgentHub multi-agent communication

TypeScript SDK for 1Claw Vault — secret management for AI agents

Flow Agents — a Kontour product that applies Flow and Veritas discipline as a portable process layer inside the agent tools you already use: Claude Code, Codex, Kiro, opencode, pi, and GitHub Actions — with framework adapters (AWS Strands preview) on the

Control what AI agents can do in your codebase

Open-source MCP server exposing Agent402.Tools' 1,407 self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answers, PDFs, OCR, images,

Step-by-step workflow enforcement for AI agents via MCP

A comprehensive library of specialized AI agents and personas for GitHub Copilot, ranging from architectural planning and specific tech stacks to advanced cognitive reasoning models.

Ctrl AI protocol reference implementation: contract/lockfile/attestation schemas, part hashing, registry client, and the init/add/verify/guard operations

TypeScript SDK for the Grantex delegated authorization protocol

Network-wide task tracking system for Wood Fired Games

ClickUp CLI for AI agents and humans

GooseWorks CLI — give your coding agent real data tools