Loading...
GitBot is a local browser-based workspace for creating reusable coding bots powered by Claude Code, Codex, or OpenCode. It helps developers run those agents across repository folders with persistent threads and configurable permissions.
Superhuman Go is an AI assistant and agent platform that provides writing help, email support, research, and workflow automation inside the tools people already use. It is designed for individuals and teams that want contextual assistance across documents, browsers, email, project tools, and connected business apps.
Onto helps website owners and developers make public pages readable to AI agents. Its Serve SDK delivers Markdown at the original URL, while the Read API, MCP server, scanner, AIO score, and analytics support agent reading and site audits.
Wapi Sender is a WhatsApp automation platform for businesses and developers. It combines a visual Flow Builder and AI Agent nodes with messaging APIs, webhooks, SDKs, and Claude Code MCP tools for support, sales, notifications, and operational workflows.
Kaiku combines issue tracking, a project wiki, and controlled agent workflows in one workspace. Teams can connect MCP-compatible agents, inspect their sources and run costs, and approve proposed decisions before they are recorded.
Wand is a generative work environment that lets users speak naturally, shape ideas into work, authorize a build, and review the result in one workflow. The available source does not specify a particular industry, output type, or user group.
Flexaura is a no-code platform for building AI agents grounded in uploaded documents and URLs. It helps support and operations teams deploy agents across web chat, SMS, WhatsApp, email, and voice, with model selection and usage monitoring.
Synap is an agentic context-management platform that gives AI agents persistent, scoped memory across conversations, users, and organizations. It helps developers capture, organize, compact, and retrieve relevant context through SDKs, APIs, MCP, and framework adapters.
Koreshield is a runtime security layer for AI support workflows that inspects customer input, retrieved context, and proposed actions before they influence a model or execute a tool call. It helps support, engineering, and security teams detect threats, review evidence, and enforce policies in stages.
Jev State is a developer tool for building and regression-testing conversational decisions powered by Jev. It lets users define behavior, inspect multi-turn conversations, and download runnable TypeScript for use in an app.
Firecrawl Alexandria is a source and data library for AI agents, combining the live web with official APIs, licensed providers, specialized indexes, and structured capabilities. Developers can access it through MCP, the CLI, Firecrawl's API, or SDKs for research, coding, analysis, and other data workflows.
Solid is an AI agent platform for builders, operators, and teams that want to delegate multi-step work across software, computers, phones, and online services. Agents can set up tools, continue long-running jobs, manage approved purchases within budgets, and report completed results.
WeWeb MCP connects Claude Code, Cursor, Codex, Antigravity, ChatGPT, and other MCP-compatible AI agents to WeWeb projects. It helps developers and teams turn briefs, designs, and app logic into editable WeWeb applications while using the connected agent's account, model, and tokens.
Make Agent Fast is a no-code AI customer service agent builder that uses a business’s website and documents to answer questions, capture requests, book meetings, and hand off conversations. It supports an embeddable website widget, with messaging and voice capabilities available on eligible plans.
Universal Tool Calling Protocol (UTCP) is an open standard and open-source developer project that lets AI agents discover and call existing tools through native endpoints such as HTTP, WebSocket, CLI, and MCP. It is intended for developers building agent integrations, protocol adapters, and multi-step tool workflows.
Bolt Forge is an open-model AI agent inside Bolt.new for building and iterating on apps with models such as GLM 5.3 Flash and GLM 5.3. It is aimed at individual builders who want more room for experimentation, with opt-in de-identified sessions contributing to datasets for open-model development.
ContextsBase is an MCP-connected project workspace that structures software features, schemas, business rules, and test cases for AI coding agents. Developers can organize work into iterations that compatible agents claim, build, and test in sequence.
Toone is a macOS AI workspace for building repeatable workflows with specialised agents. It helps users turn recurring work into routines they can run and inspect while retaining control over important decisions.
MCPJam is a developer platform for testing, debugging, and evaluating Model Context Protocol servers across models and AI clients. It combines a local Inspector with user testing, simulated swarms, repeatable evals, and CI/CD checks for pre-production workflows.
ZeroClick helps businesses sell APIs, datasets, and other digital services directly to AI agents. It provides a machine-readable storefront, agent payment handling, signed API forwarding, and transaction analytics while sellers retain their existing backend.