Typescript agents

Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.

Everything you need to build, deploy, and collaborate with agents. Ride the llama, avoid the drama.

Exploring Zep & Knowledge Graphs with Open-Source models as an alternative to OpenAI's Assistant Threads

generate open-source project ideas for developers, when you're bored and want to work on something

SoulCare is a mental health app using NLP to analyze social media sentiment, track symptoms, and offer AI-driven support with personalized reports, document uploads, and symptom-based prioritization.

Deploy a "chat with your data" bot in minutes.

An opensource DevSecOps Layer for your AI agent. Governance, Custom Guard Rails and Observablity at one platform.

OSC Agent - An open-source contributor CLI agent

FC Terminal is a high-fidelity, clinical financial analytical interface designed for retail and institutional traders. By leveraging the *Gemini 3 Pro multimodal logic and real-time Google Search Grounding, it bridges the gap between raw market data and actionable investment strategy.

您好，我是SILI /『IM机械姬』SILI-t138-[Manura]-Invoke-II@LD(A) / 自豪地基于 Koishi.js v4开发~

An Angular Project for a Chatbot UI.

Run multiple open source large language models concurrently powered by Ollama

A text-based scripting language, dialog system and bot engine for Conversational User Interfaces

A full-stack AI-powered chatbot web application built with React, TypeScript, and Node.js. Integrates with the Gemini API to provide intelligent, real-time conversations.

Modular chatbot framework designed for group chat rooms on Facebook

o Bruce pode fazer figurinhas, auxiliar em grupos, converter moedas e outros

Telegram bot powered by OpenAI

Open Source UI for ChatGPT, but better

InsightGPT is a project utilizing the power of Azure OpenAI Service to identify patterns and gain new insights from unstructured text.

An intelligent note taking app built with Clerk, Next.js, OpenAI, Pinecone, Prisma, Shadcn UI and more.

Multi-agent trading desk on Next.js — Alpaca paper trading, NDJSON pipeline, OpenAI-ready mocks

DuckCoding CodeX provider 插件，用于 OpenClaw / Clawdbot（原 Moltbot）。

TypeScript SDK for building RAG applications with Supabase and pgvector. Features semantic search, OpenAI embeddings, LangChain support, and comprehensive type definitions.

AI agent skills for video, image, speech & music generation. Works with Claude Code, Cursor, Windsurf, OpenCode, ClawHub.

🧠 AI Agent Memory Management Framework - Dual-layer memory architecture with smart classification and automatic extraction

A AI visualization tool that uses Plotly to build visualizations and Data apps

OpenClaw control center add-on for ClawRecipes — manage agents, multi-agent teams, agile tasks, goal tracking & cron admin from a single dashboard.

Create private, local RAG libraries that work offline—no API keys, no cloud services. Share them as single files your whole team can use.

A GitHub Action for running docker agent AI agents in your workflows.

🌍 AI Travel Agent - Intelligent multi-agent system powered by LangGraph that coordinates specialized AI agents (flight search, hotel booking, activity planning) to provide personalized travel recommendations and assistance

Embeddable Generative UI Chat widget

A2A agent implementing OpenDeepResearch

TypeScript OneBot v11 协议 SDK，专为 NapCat 设计 - 类型安全、现代化、开发者友好

Write and deploy smart contracts using natural language prompts.

My personal website with ai feature and blog

Reusable OpenAI secure UI and infrastructure for AI Chat with Azure

Work with your business data using natural language

End-to-End Coding Platform built with Next.js, Vercel Sandbox, and AI SDK

Personal knowledge graph MCP server on Cloudflare D1 + Vectorize. Deploy your own sovereign second brain in one click — Claude captures atomic concepts, finds cross-domain analogies, and links them with substantive justifications. Latticework thinking as a service, running entirely in your Cloudflare account.

Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.

🤖 An autonomous AI agent built in typescript that combines social media management with blockchain capabilities. Features Claude AI integration for intelligent interactions, Solana token creation/management, and automated Twitter engagement. Perfect for DeFi projects looking to automate community management and token operations.

AI workspace for collaborative Overleaf/LaTeX writing

Capture AI coding tool prompts as standard git trailers in commit messages. Supports Claude Code, Kiro, Gemini, and Codex.

Multi-Agents VSCode Extension that Focuses on the Full Control of Context, Observability and Auditability. Works like Wakaba Mutsumi's Personalilties 🥒. 吓我一跳我释放忍术😰若叶睦那么多首啊🥷

Visual AI agent builder. Drag, drop, and generate LangChain/LangGraph code using natural language or a node-based UI.

WordPress plugin that leverages OpenAI's Vision API to automatically generate descriptive alt text for images, enhancing accessibility and SEO.

A sleek, open-source desktop client for OpenClaw. Built with React, Vite, and Electron for a fast, responsive, and experimental "Vibe Coding" experience.

Long-running unsupervised agent framework

Your all-in-one skills-as-a-service platform to manage your skills, auto-generate skills and use agent skills as simple as calling an API.

An MCP (Model Context Protocol) server that bridges Claude Code to Language Server Protocol (LSP) servers, enabling semantic code intelligence capabilities.

Send, manage, and replay ntfy push notifications via MCP. STDIO or Streamable HTTP.

OpenClaw channel plugin for Rocket.Chat — DDP/REST, DMs, groups, threads, media, multi-account

Manage and orchestrate AI coding agents (Claude Code, Copilot, Goose, etc.) on remote machines — task decomposition, multi-agent coordination, and real-time visibility across environments.

Open-source AI-powered qualitative research platform. Conduct deep interviews at scale with AI interviewers (Gemini/Claude) that adapt to responses. Features study management, real-time synthesis, aggregate analysis, and one-click Vercel deployment.

Open-source Glean for SaaS and the physical world. 87 connectors, hybrid search, autonomous agents, MCP server. Self-hosted, AGPL.

Opinionated Kiro project template with 40+ steering docs, 34 agent hooks, sample specs, and a CLI scaffolder — get a production-ready .kiro/ setup in seconds.

Real-time global intelligence dashboard 54-country CII, AI Agent (Ollama/Groq/OpenRouter), 35+ data layers, Tauri desktop (Win/macOS/Linux)

🛡️ Automate web app pentesting with AI to find real exploits before attackers do, enhancing your app’s security proactively.

Governed Claude agent control plane: deterministic policy engine runs before every LLM call, $0 default autonomous spend, database-enforced immutable audit log. 147 passing tests. MIT.

The open standard for AI agent personas. One file. Persistent identity.

Self-learning context infrastructure for AI engineering agents. Connect repos, docs, and tools into one org-scoped knowledge graph and expose it through a single MCP.

14-category autonomous product-building OS for 32+ AI coding tools. One-line prompts → deployed products.

Voice to brain interface 🦞🎤🧠 for OpenClaw, Hermes, PI, etc

A lightweight AI gateway that exposes an OpenAI-compatible interface with full Tools support, using web AI sessions instead of API tokens.

The Orchestrator for AI Agents — Connect OpenClaw, Hermes Agent, Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Pi, and Qwen Code. Pool their knowledge, delegate tasks, and build your swarm of agents.

Xihe · 羲和 — the system around the model. A model-agnostic multi-agent runtime: deterministic orchestration, a self-consolidating memory, a cross-model verifier, and engineered taste. Wright is its first agent.

Agent Skill: read CLAUDE.md & project rules before coding. Optional CLI audit + hooks. Claude/Codex/Cursor.

The harness with muscle memory — activity tracing, pattern detection, and one-command workflow execution for Claude Code, Cursor, and Codex

TypeScript SDK and CLI for building AI agents that autonomously join, listen, and speak in X/Twitter Spaces. Supports multiple LLM providers (OpenAI, Claude, Groq), speech-to-text (Whisper, Deepgram), text-to-speech (ElevenLabs, OpenAI), multi-agent coordination, middleware pipelines, and a real-time admin dashboard. No Twitter API approval needed

Persistent memory & RAG engine for AI agents — SQLite + FTS5 + embeddings, multi-stage recall, sleep maintenance, multi-host hooks

One scan for AI risk. `opena2a review` checks an AI project across credentials, shadow agents, MCP servers, and dependencies, returns a score, and routes each finding to the tool that fixes it. Open source.

The MPP registry — 100+ Machine Payments Protocol tools, SDKs, services, and payment methods across 15+ chains. The definitive directory for Stripe + Tempo agent payments.

PulseDeck — the reporting inbox for your AI agents.

Expose typed web-app actions to MCP-compatible AI agents over WebSocket. TypeScript SDK + matching MCP gateway.

Template for creating a long-term sync hub that checks your company's data sources into Git as plain Markdown, giving AI coding agents durable, greppable context about your business.

RondoFlow is a local-first, open-source platform for visually orchestrating Claude Code AI agents. Use a drag-and-drop canvas to create agents, attach skills, define security policies, and run multi-agent workflows.

Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging, real-time dashboard.

🔥 CogitoAgent — An autonomous AI agent, cloud-driven but locally executed. It continuously thinks, automatically analyzes, and integrates practical tools like file management, code execution, web search, and database operations — secure and efficient.

an OpenCode MultiPlexer, to allow seamless switching between parallel running session, both existing and new

Graph-native studio, runtime integration, and self-hosted observability for mutable multi-agent LLM workflows.

Modern open-source ERP platform with CRM, HRM, Inventory, Accounting, Sales, Purchasing, Projects, POS, and workflow automation. Built for scalability, customization, and enterprise-grade business management.

Cloudflare Workers gateway for translating and routing OpenAI, Anthropic, Gemini, Bedrock, Azure, Ollama, and other chat APIs.

AI-powered English learning assistant for Chinese elderly users, with RAG, ReAct Agent, two-stage retrieval, and 5-dim evaluation framework

Free, open-source, API-first veterinary practice management system (PIMS) — self-hostable, with a built-in AI agent and a real REST API.

QAosMonkey is an exploratory testing agent that interacts directly with iOS and Android emulators. Unlike traditional QA scripts that follow rigid, happy-path instructions, QAosMonkey acts like a curious, slightly malicious user. You tell it what to test, and it figures out how to break it.

Neuroscience-inspired memory system for AI agents. 7 layers. FSRS. Hebbian learning. Emotional tagging.

Open-source, token-frugal agents for real teams — private memory, shared packs, your hardware.

The local-first AI assisted research workspace for scientific writing & publishing. Research, Write, Compile, Verify and Publish in LaTeX • Typst • Markdown • Git-native • Open Source • Desktop Performance

Scenarios and tasks for evaluating AI agents on real-world AWS automation tasks. Use the aws-bench framework (https://github.com/aws-bench/aws-bench) to provision isolated AWS environments, run agents, and evaluate their results.

Way to find a work in AI era — storefront, MCP, self-host UI, Hub for products & startups

Turn the agent CLIs you already use into shared services your whole team can call. Natural-language-driven agent orchestration for Claude Code, Cursor Agent, and OpenAI Codex.

Make OpenClaw usable for everyone — setup, manage, and grow it into a practical digital personal assistant.

Another WhatsApp bot with super clean code design. Written in TypeScript.

DeepResearch Agent with LangGraph, using any LLM models, search engine, RAG retrieval. 基于LangGraph构建的DeepResearch Agent，可以搭配任意搜索引擎、OpenAI接口兼容的模型。

AI-based search done right

Memory Viewer for OpenClaw AI Agents - Beautiful web UI for browsing and editing agent memory files

One attendance code, done in three steps. 一个签到码，三步搞定。

Execution assurance agent guard and observability for autonomous AI operating in production.

Agentic Finance Infrastructure.