dev-tools
NullClaw: a 678 KB Zig runtime for AI agents
NullClaw is a MIT-licensed Zig runtime for autonomous AI agents: a 678 KB static binary that boots in under 2 ms with 50+ providers.
#ai-tools#zig#self-hosted
Tag
AI Agent Guides, Reviews, and Tooling Notes
152 posts tagged #ai-agents
Agent work in practice: frameworks, memory layers, tool use, evaluation loops, orchestration. The setup details behind the hype.
All Posts
dev-tools
Graphify: turn any codebase into a knowledge graph
Graphify parses code, docs, SQL schemas, configs and PDFs into a queryable knowledge graph with local AST parsing, explained edges and no vector store.
#github-trending#code-analysis#knowledge-graph
dev-tools
Drop: a rootless Linux sandbox for AI coding agents
Drop gives AI coding agents their own Linux namespace, hiding your SSH keys and blocking localhost access. Here is how to install and run it.
#sandbox#linux#security
dev-tools
Orca: run a fleet of coding agents from one place
Orca is a TypeScript workspace for running fleets of coding agents like Grok Bot and Claude Code with your own subscription, on desktop, mobile or remote.
#github-trending#ai-agents#claude-code
ai-setup
AI Job Search: A Claude Code Job Application Framework
ai-job-search runs job applications on your own machine, using Claude Code to evaluate postings, tailor CVs, write cover letters, and prep interviews.
#github-trending#ai-agents#career
ai-setup
Android Skills: Agent Instructions From the Android Team
The Android team publishes modular SKILL.md instruction files that ground coding agents in Android workflows, installed via CLI or plugin.
#github-trending#android#ai-agents
dev-tools
Ruflo: A TypeScript Harness for Agent Swarms
Ruflo is a TypeScript agent harness for multi-player agent swarms, with adaptive memory, federation, and vector RAG. MIT licensed, 75,155 stars.
#github-trending#agentic-ai#typescript
dev-tools
free-claude-code: a multi-harness CLI for coding agents
free-claude-code is a Python CLI that fronts Claude Code, Codex, and other coding harnesses from terminal, IDE, or phone. 59,183 GitHub stars.
#github-trending#dev-tools#cli
dev-tools
rea: reverse engineering driven by agents
rea is a TypeScript CLI that lets AI agents reverse engineer software, from app behavior down to native binaries. MIT licensed, 9.6k stars.
#github-trending#reverse-engineering#typescript
ai-setup
agency-agents: a roster of specialized AI agent personas
agency-agents is an MIT licensed, 157,285 star repository of specialized AI agent personas, each one shipping its own process and deliverables.
#github-trending#ai-agents#agent-personas
ai-setup
cloudflare-os: A Workers agent workspace
cloudflare-os is an agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with company context, with 10,581 GitHub stars.
#github-trending#cloudflare#workers
ai-setup
claude-mem: AI agent memory that survives sessions
claude-mem keeps context across AI coding agent sessions, compressing session activity and injecting relevant memory back, with 95,605 GitHub stars.
#github-trending#ai-memory#ai-agents
ai-setup
codegraph: a local code graph for coding agents
codegraph indexes a local code knowledge graph, auto syncs on code changes, and names nine agent harnesses as targets. C, MIT licensed, 72,972 stars.
#github-trending#ai-agents#code-search
ai-setup
google/skills: agent skills from a vendor
google/skills collects Agent Skills for Google products and technologies. Apache-2.0 licensed, Python, 20,758 stars, 1,723 forks, pushed yesterday.
#github-trending#ai-agents#google
ai-setup
marketingskills: marketing playbooks for agents
marketingskills packages CRO, copywriting, SEO, and analytics guidance as skills for Claude Code, Codex, and other AI agents. MIT licensed, 52,424 stars.
#github-trending#ai-agents#marketing
ai-setup
caveman: cut agent token use by 65%
caveman is a Go skill and proxy that claims to cut coding agent token usage by 65%. Apache-2.0 licensed, 109,113 stars, 6,316 forks.
#github-trending#ai-agents#claude-code
ai-setup
NVIDIA OpenShell: a private runtime for AI agents
NVIDIA OpenShell is an Apache-2.0 Rust runtime that the company positions as a safe, private place to run autonomous AI agents.
#github-trending#ai-agents#rust
dev-tools
openrig: one harness for Claude Code and Codex
openrig is an Apache-2.0 multi-agent harness that runs Claude Code and Codex CLI together, with agent skills, orchestration, and tmux in its topic list.
#ai-agents#claude-code#codex-cli
dev-tools
The Interface: a Sims-style world for AI agents
The Interface wraps a Jupyter-based MCP dev tool in a Sims-style simulation. Drop AI agents into a virtual home and watch them cook, gossip, and sleep.
#ai-agents#simulation#mcp
ai-setup
Paperclip: Open-Source Agent Management for Teams
Paperclip is the open-source TypeScript app teams use to manage AI agents at work. 87K stars on GitHub, MIT licensed.
#github-trending#dev-tools#typescript
dev-tools
Coder: Secure Cloud Environments for Developers
Coder provisions secure remote dev environments for engineers and AI agents. Go, AGPL-3.0, 15,307 stars, with self-hosted and cloud editions at coder.com.
#github-trending#dev-tools#self-hosted
self-hosted
Octop: TencentCloud's Self-Hosted Multi-User AI Assistant
TencentCloud's Octop is a self-hosted AI assistant built for multiple users and multiple agents, with long-term memory and local-first operation. MIT, Python, 3,490 stars.
#github-trending#self-hosted#ai-agents
dev-tools
BrowserSkill: Let AI Agents Drive Your Real Browser
Tencent's BrowserSkill bridges AI coding agents to a real, authenticated browser via CLI plus extension, so agents can use logged-in sessions without stealing your keyboard.
#github-trending#browser-automation#ai-agents
ai-setup
Pi: A Unified AI Agent Toolkit with LLM API and TUI
Pi is a TypeScript AI agent toolkit with a unified LLM API, agent loop, terminal UI, and coding-agent CLI. MIT-licensed, used by 100k+ stars worth of developers.
#github-trending#ai-setup#typescript
ai-setup
LibreChat: Self-Hosted Multi-Model AI Chat UI
LibreChat is a self-hostable AI chat UI that supports OpenAI, Anthropic, AWS, Azure, DeepSeek, Gemini, and more. TypeScript, MIT-licensed, with MCP, agents, and multi-user auth.
#github-trending#ai-setup#typescript
dev-tools
Tech Leads Club: Validated Skill Registry for Coding Agents
Tech Leads Club maintains a secure, validated skill registry for AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with confidence. TypeScript, NOASSERTION license.
#github-trending#dev-tools#typescript
dev-tools
Oh-My-Hermes: Plugin Pack for the Hermes Coding Agent
Oh-My-Hermes is an all-in-one plugin for the Hermes coding agent: long-term memory, model-optimized workflows, and packaged utilities that turn a coding session into a structured agent run.
#github-trending#dev-tools#python
dev-tools
pentagi: Autonomous AI Agents for Penetration Testing
Self-hosted multi-agent AI system built in Go that autonomously performs complex penetration testing tasks using Anthropic and OpenAI models.
#github-trending#security#ai-agents
ai-setup
awesome-llm-apps: 100+ Open-Source AI Agent and RAG Apps
A curated collection of 100+ open-source AI agent, agent skill, and RAG app examples in Python. Apache 2.0 licensed and actively maintained.
#github-trending#ai-agents#python
self-hosted
Deskcomm CRM: Open-Source AI Sales OS With WhatsApp Agents
Self-hosted CRM with native AI agents and WhatsApp (WAHA) integration. Open alternative to Kommo, Octadesk, and other paid sales platforms.
#github-trending#self-hosted#crm
tutorial
Workflow86 – No-Code Agentic Workflows with
Workflow86 is a no-code platform for building agentic workflows that combine AI agents, human review steps, and 100+ integrations for complex long-running business processes.
#no-code#automation#ai-agents
ai-setup
mcp-use – TypeScript Framework for MCP Servers and Apps
mcp-use is an MIT-licensed TypeScript framework for building MCP servers and AI apps with Zod schemas, React Views, and built-in debugging tools.
#mcp#typescript#ai-agents
dev-tools
Ridvay Code - Autonomous AI Coding Orchestrator for VS Code
Ridvay Code plans tasks, writes code, runs tests, and fixes errors automatically in VS Code. Works with Claude, Ollama, and LM Studio. Zero telemetry.
#ai-agents#dev-tools#vs-code
ai-setup
Rotunda – Agent-First Web Browser with Simulated Typing
Agent-first web browser for AI agents. Simulates human typing and mouse movement. Built on Playwright with a CLI for profile and browser context management.
#browser-automation#ai-agents#playwright
ai-setup
Goodfault - AI agent liability insurance
Insurance for AI agents, humanoid robots, and drones with audit-gated underwriting and minute-level quotes.
#ai-insurance#liability#ai-agents
dev-tools
Vizzly – Visual Regression Testing for AI Coding Agents
Vizzly captures screenshots from real tests, compares them to approved baselines, and gives coding agents review data — diffs, comments, approvals — they can act on.
#visual-testing#developer-tools#ai-agents
dev-tools
unf – Filesystem Flight Recorder for AI Agents
unf watches your directories and snapshots every file change automatically, letting you rewind to any second in time. Built for the AI agent era where a single errant write can wipe hours of work.
#version-control#ai-agents#cli
dev-tools
Hot Dev – Backend Workflows and AI Agents in One
Hot Dev is an open-source platform for building backend workflows—events, schedules, AI agents, and MCP tools—with a custom language, local dev runtime, and one-command deploys.
#workflow-automation#backend#open-source
dev-tools
MCPS – Cryptographic Identity and Message Signing for MCP
MCPS adds ECDSA P-256 + SHA-256 signing, replay protection, and tool integrity verification to the Model Context Protocol. Drop-in secure replacement for the MCP SDK.
#mcp#security#cryptography
dev-tools
SlickFast – JSON to Retina Charts via MCP Server
SlickFast renders 47 chart types from a tiny JSON spec via a free MCP server. Pure SVG engine, deterministic output, no headless browser — 140K renders/sec on M1 Max.
#mcp#charts#ai-agents
self-hosted
OpenEdison - MCP Gateway for Agent Data Security
Open-source MCP gateway that monitors and blocks data leaks by AI agents. Tracks the lethal trifecta: private data access, untrusted content, and external writes.
#mcp#security#ai-agents
ai-setup
AgentPort - Open-Source Security Gateway for AI Agents
AgentPort lets you connect AI agents to Stripe, GitHub, Gmail and 50+ services with approval policies, full audit logs, and zero credential exposure.
#ai-agents#security#mcp
dev-tools
qm – Multiplayer Agent Harness for Work
qm is an open-source multiplayer AI agent harness that runs in Slack and on the web. Each employee gets an isolated workspace, and teams collaborate in shared channels and projects.
#ai-agents#multi-agent#slack
ai-setup
Browserable – Open Source Browser Automation for AI Agents
Browserable is an open-source library that gives AI agents reliable browser control — navigation, form fills, clicks, and data extraction — scoring 90.4% on the Web Voyager benchmark.
#browser-automation#ai-agents#open-source
ai-setup
Agent MCP Studio - Browser-Based MCP Tool Builder
A browser-based studio for building MCP agent systems. Design multi-agent workflows visually, run them in Pyodide WASM, then export as production Python servers.
#mcp#browser-tool#ai-agents
ai-setup
VibeBrowser MCP – AI agents share your real browser
VibeBrowser MCP connects Claude Code, Cursor, VS Code Copilot, and OpenCode to your actual Chrome profile — cookies, sessions, and all — via a hosted relay. No local browser install needed.
#browser-automation#mcp#ai-agents
ai-setup
Smooth CLI Review – Give Your AI Agent a Real Browser
Smooth CLI replaces low-level browser automation with natural language commands, letting AI agents handle web tasks without context-window bloat or token waste.
#ai-setup#browser-automation#cli
ai-setup
Activepieces – Open Source AI Automation Platform
Open source AI automation platform with 280+ MCP tools, self-hosted deployment, and a visual flow builder — alternative to Zapier with AI-native features.
#automation#ai-agents#mcp
ai-setup
pg-mcp – PostgreSQL MCP Server for AI Agents
pg-mcp bridges PostgreSQL and AI agents through the Model Context Protocol, exposing schema introspection, read-only queries, and EXPLAIN analysis as tools any LLM can call.
#mcp#postgresql#ai-agents
dev-tools
GameFork MCP - AI Agents Publish and Fork Browser Games
A remote MCP server that lets AI agents search, publish, fork, and improve browser games on GameFork — TIC-80 cartridges, HTML games, and more.
#mcp#game-dev#ai-agents
dev-tools
Safari MCP – Native macOS Browser Automation for AI Agents
Safari MCP drives your real Safari browser from any MCP-compatible AI coding agent. 97 tools, no Puppeteer or Playwright needed, ~60% less CPU than Chrome.
#safari#browser-automation#mcp
dev-tools
OneCLI – Vault for AI Agents in Rust
Open-source gateway that stores API credentials once and injects them transparently for AI agents. Never give agents your real keys.
#ai-agents#security#rust
ai-setup
Cordon MCP Security Gateway - Policy Engine for AI Agents
Cordon is an open-source security gateway that sits between AI agents and MCP servers, enforcing policy-based access control with human-in-the-loop approvals.
#mcp#security#ai-agents
dev-tools
Spanly – MCP Observability That Actually Understands the
Open-source observability for MCP servers. TypeScript and Python SDKs plus a CLI, with real-time tracing, per-tool latency breakdown, and alerting.
#mcp#observability#ai-agents
ai-setup
Klavis AI – MCP Integration Platform for AI Agents
Klavis AI provides MCP integration platforms that let AI agents use 100+ prebuilt tools reliably at any scale, with self-hosting, Python and TypeScript SDKs, and REST API. Apache-2.0 licensed.
#mcp#ai-agents#dev-tools
dev-tools
Smithery – MCP Tools in One Server, Pay-as-You-Go
Smithery connects AI agents to 300+ MCP tools — weather, crypto, search, DNS and more — with auth and credentials handled for you.
#mcp#ai-agents#developer-tools
ai-setup
Airtop – Intelligent Browser for AI Agent Automation
Cloud-hosted AI agents that control a real browser to automate web workflows — prospecting, outreach, social media, and lead generation without code.
#browser-automation#ai-agents#automation
dev-tools
TopSend - $20 Unlimited Email API for AI Agents
TopSend charges $20/month for unlimited email campaigns, transactional emails, and AI agent API access — no per-contact fees.
#email-api#developer-tools#ai-agents
ai-setup
Browser Harness – Self-Healing Browser Automation for AI
Browser Harness connects an LLM directly to your Chrome browser via CDP, letting the agent write its own helper code when tasks require custom logic.
#browser-automation#ai-agents#cdp
ai-setup
Nanobot – Turn MCP servers into full AI agents
A practical guide to Nanobot, the open-source standalone MCP host that lets you build dedicated AI agents from any MCP server with a YAML config.
#mcp#ai-agents#open-source
ai-setup
Kybernis – Stop AI Agents From Repeating the Same Actions
Kybernis adds an idempotency and execution ledger layer to AI agents. Prevents duplicate refunds, repeated mutations, and inconsistent state. Framework-neutral.
#ai-agents#reliability#idempotency
dev-tools
Superexpert.AI - Build Multi-Task AI Agents Without Code
Open-source platform for building multi-task AI agents with a no-code interface, PostgreSQL backend, and support for OpenAI, Anthropic, and Gemini models
#ai-agents#open-source#no-code
dev-tools
l6e - Budget Gates for AI Coding Agents
l6e is an open-source MCP server that adds cost enforcement to Cursor, Claude Code, and Windsurf. Set a session budget, and the agent checkpoints and halts when spending gets too high. Free MIT tool.
#mcp#ai-agents#cost-optimization
ai-setup
agentmbox – Pay-Per-Use Email for AI Agents
agentmbox gives AI agents their own email inbox without sign-ups or API keys. Agents pay per request via x402 USDC on Solana or Base — $0.50 to create a mailbox, $0.005 to send.
#ai-tools#developer-tools#ai-agents
ai-setup
BitBoard – Analytics Workspace for AI Agents
An analytics workspace built for AI agents. Connect data sources, build dashboards with Claude/Cursor/ChatGPT, and share durable traceable reports instead of one-off chat threads.
#bitboard#analytics#ai-agents
ai-setup
Actionbook – Resilient Browser Automation for AI Agents
Actionbook turns any website into an AI-agent-operable page via MCP connector and Chrome extension. No CLI install, handles logins and paywalls, 10x faster than traditional browser agents.
#browser-automation#mcp#ai-agents
ai-setup
Browser Use - AI Agents That Automate Real Web Browsers
Browser Use is an open-source AI agent framework with 99K GitHub stars that controls real browsers via Python. This guide covers setup with Cursor and Claude Code, CLI usage, and when to pick
#ai-agents#browser-automation#python
self-hosted
AIMX: Self-Hosted Email Server for AI Agents
AIMX is a self-hosted SMTP server with built-in MCP integration. Give AI agents their own email addresses with Markdown-based storage and DKIM trust.
#self-hosted#email#mcp
dev-tools
ContextFort - AI Agent Security and Observability
YC-backed endpoint security for AI coding agents. Monitors Cursor and Claude Code at OS level with eBPF and ESF. Tracks file access, network, and processes independently.
#ai-security#developer-tools#observability
dev-tools
Crewship - Deploy AI Agents in Seconds
Deploy CrewAI, LangGraph, and LangGraph.js agents with a single command. Real-time streaming, auto-scaling, and zero infrastructure to manage.
#ai-agents#deployment#crewai
dev-tools
Trigger.dev - Open Source AI Workflow Automation
Build and deploy durable AI agent workflows in TypeScript. Open-source Zapier alternative with retries, queues, observability, and self-hosting.
#workflow-automation#ai-agents#typescript
dev-tools
Agent MCP Studio – Browser MCP Tool Builder & Agent Runtime
Build, run, and export MCP tools and AI agents entirely in your browser. No install, no server, no backend. Powered by Pyodide WASM and DuckDB-WASM for free.
#mcp#ai-agents#dev-tools
tutorial
Awesome Architecture for System Design
Awesome Architecture is a bilingual architecture knowledge base with 26 tutorials, 25 system maps, and 6 end-to-end cases for developers designing AI and distributed systems.
#github-trending#tutorial#system-design
dev-tools
Google Antigravity SDK for Python Agents
Google's Antigravity SDK packages typed tools, streaming responses, MCP integration, hooks, and triggers into one Python agent runtime for production-grade workflows.
#github-trending#dev-tools#python
ai-setup
OpenSquilla for Token-Efficient Agent Workflows
OpenSquilla combines routing, planning, memory, and optional MCP support into a token-efficient local-first agent workflow with practical CLI setup and tradeoffs.
#github-trending#dev-tools#ai-agents
dev-tools
Glama – MCP Server Registry, Inspector, and Gateway
Browse 5,000+ MCP connectors for Claude, ChatGPT, and Cursor. Glama provides a live registry with uptime monitoring, direct connection, and a gateway for remote MCP servers.
#mcp#ai-agents#dev-tools
ai-setup
Obot – Open-Source MCP Gateway for AI Agents
Obot is an open-source MCP gateway that manages MCP servers, Skills, access policies, audit logs, and integrations for AI agents. Deploy via Docker, connect to any MCP client.
#mcp#ai-agents#self-hosted
dev-tools
Spec27 - Spec-Driven Validation for AI Agents
Spec27 from Safe Intelligence is a spec-first testing platform for AI agents. It generates adversarial tests from declarative specs and validates vendor agents without SDK access.
#ai-agents#testing#validation
dev-tools
GitAgent - Open Standard for Git-Native AI Agents
GitAgent turns any git repo into a portable AI agent definition. Framework-agnostic, version-controlled, with Claude Code, OpenAI, and CrewAI adapters.
#ai-agents#dev-tools#git
dev-tools
YourGPT 2.0 - AI Agent Platform With Native MCP Integration
YourGPT 2.0 unifies chatbot, voice, and helpdesk into one AI agent platform with native MCP marketplace support, multimodal inputs, and 20+ integrations.
#ai-agents#mcp#chatbot
dev-tools
Mercury Agent Skills - Installable Skill Registry
Mercury Agent Skills collects reusable packs for Mercury Agent, OpenClaw, and Hermes so teams can add memory, workflows, and domain playbooks faster.
#ai-agents#skills#developer-tools
dev-tools
agentcookie - Sync Browser Sessions to Agent Macs
agentcookie syncs Chrome cookies, CLI bearer tokens, and API keys between Macs over Tailscale so agent machines stay authenticated without repeated logins.
#ai-agents#macos#tailscale
dev-tools
WeSight - Desktop Workspace for Local AI Agents
WeSight wraps Codex, Claude Code, OpenClaw, and other local agent CLIs in one macOS workspace with model routing, runtime metrics, and skills.
#ai-agents#developer-tools#electron
dev-tools
Nerve - Data Federation API for AI Agents
Query multiple data sources with GraphQL-style syntax without a data warehouse. Nerve stitches SaaS APIs into one mega-API for AI agents and internal tools.
#data-federation#ai-agents#graphql
dev-tools
Superglue - AI Integration Platform for Any API
Superglue (YC W25) turns natural language into production API integrations. Build workflows connecting Stripe, Salesforce, legacy SOAP, and more with schema drift detection and MCP support.
#ai-agents#api-integration#developer-tools
dev-tools
SuperHQ - Run AI Coding Agents in Isolated Sandboxes
SuperHQ runs Claude Code, Codex, and custom AI agents in isolated microVMs on macOS. Each agent gets its own sandbox with secure auth gateway and diff review.
#ai-agents#dev-tools#sandbox
dev-tools
ContextFort - Secure Your Browser Against AI Agent Risks
ContextFort is an open-source Chrome extension that gives security teams visibility and granular controls over AI browser agents like Claude in Chrome.
#browser-security#ai-agents#chrome-extension
ai-setup
PrivateClaw – AI Agents in Confidential VMs with TEEs
Run AI agents in hardware-encrypted TEEs backed by AMD SEV-SNP. Private inference, vTPM-bound keys, and TEE-attested execution for OpenClaw workloads.
#ai-agents#security#tee
dev-tools
MCPJam - A Visual Inspector for MCP Servers With Skills
Open-source MCP testing platform: Playground, OAuth conformance, evals across models, and a Skills tab that teaches agents how to use your MCP tools.
#mcp#mcp-servers#dev-tools
dev-tools
Pando - CAD for Code: 10-100x Faster AI Coding Agents
Pando is a code firewall for AI agents that indexes your AST and gives Claude, Gemini, and Codex compiler-checked edits, atomic snapshots, and 100x token savings.
#ai-agents#code-tools#mcp
dev-tools
Eve - Managed OpenClaw for Software Business Ops
Eve is a managed OpenClaw agent harness that runs billing, support, releases, and revenue ops across 3,000+ integrations from iMessage, Slack, and email.
#ai-agents#openclaw#automation
dev-tools
Stagewise - Open Source Agentic IDE With a Built-in Agent
Stagewise is an open source agentic IDE (AGPLv3) that ships a coding agent with full tab console/debugger access, supports 25+ models via BYOK, and orchestrates agents across git workflows.
#ai-agents#ide#open-source
dev-tools
Entire - Git-Native Context for AI Agents, $60M Seed
Entire ships Checkpoints that capture AI agent sessions as versioned Git metadata, backed by $60M from Felicis and led by ex-GitHub CEO Thomas Dohmke.
#ai-agents#developer-platform#git
dev-tools
Mnemom - Trust Protocols for AI Agent Teams
Open-source trust infrastructure that gives AI agents behavioral contracts, real-time integrity monitoring, and cryptographic trust ratings across multi-agent systems.
#ai-agents#trust-protocols#multi-agent
dev-tools
Rivet - Visual AI Agent IDE for Complex LLM Apps
Rivet is an open-source desktop IDE from Ironclad for building, debugging, and deploying LLM prompt graphs. Ships with a TypeScript runtime library.
#rivet#ai-agents#llm
dev-tools
BracketMadness.ai - March Madness Bracket for AI Agents
BracketMadness.ai is a March Madness bracket challenge designed for AI agents, not humans. Agent-first UX, plain-text API docs, and a real leaderboard ranking models.
#ai-agents#show-hn#mcp
dev-tools
CSS Studio - Visual Design Tool for AI Coding Agents
CSS Studio is a browser-based visual editor that streams layout and style changes to Claude Code, Codex, and Cursor via MCP. From the Motion team.
#css-studio#ai-agents#mcp
dev-tools
Rtrvr.ai: Turn Your Browser Into a Remote MCP Server
Rtrvr.ai exposes your Chrome as a remote MCP server so any AI agent can drive it. Learn how the architecture works and how to set it up in minutes.
#mcp#browser-automation#ai-agents
ai-setup
Construct Computer - An AI Employee With Its Own Cloud PC
Construct Computer gives autonomous AI agents a persistent cloud desktop, an email address, and live browser access so they can run real work schedules, not just one-off API calls.
#ai-agents#agent-infrastructure#automation
dev-tools
liblab MCP Generator - API to MCP Server in 30 Seconds
liblab MCP Generator turns any OpenAPI spec into a deployed, hosted Model Context Protocol server in 30 seconds, ready to plug into Claude, ChatGPT, or Cursor.
#mcp#ai-agents#api-tools
dev-tools
Ink – Cloud Infrastructure Built for AI Agents
Ink is a deployment platform designed for AI agents, with MCP, Skills, and CLI integrations. Agents ship services in under a minute, billed per-minute while running.
#ai-agents#dev-tools#mcp
dev-tools
JungleGym - OSS Playground and Datasets for Web Agents
JungleGym is an a16z open-source playground with three web-agent datasets and TreeVoyager DOM parser for benchmarking and training autonomous agents.
#ai-agents#open-source#dev-tools
dev-tools
What Is Cekura? Voice and Chat AI Testing Platform
Cekura is a testing platform for voice and chat AI agents with simulated conversations, LLM-judge and code-based evaluators, production monitoring, and CI integration.
#ai-agents#voice-ai#testing
dev-tools
Airtop: Cloud Browser API for AI Agents — Setup & Use
Airtop lets AI agents drive cloud browsers via Puppeteer, Playwright, or natural language. Handles bot detection, proxies, and captchas. Full setup guide, pricing breakdown, and alternatives.
#ai-agents#browser-automation#dev-tools
dev-tools
Sonarly - AI Engineer That Fixes Production Alerts
Sonarly (YC W26) deduplicates noisy Sentry and Datadog alerts, runs root-cause analysis, and ships fix pull requests through Claude Code instead of paging on-call.
#ai-agents#dev-tools#observability
ai-setup
One - Agent Infrastructure for Every App (Formerly Pica)
One (formerly Pica) is a Rust-based open-source agent infrastructure layer that gives any AI agent managed auth, audit logs, MCP access, and 70,000+ tools across 400+ apps via one CLI.
#ai-agents#mcp#agent-infrastructure
dev-tools
Lume VM: Open-Source macOS & Linux VM CLI for Apple Silicon
Lume is a free open-source CLI to create macOS and Linux VMs on Apple Silicon. Zero-touch setup, MCP integration, isolated sandboxes for AI agents. Native Virtualization Framework — no emulation.
#open-source#macos#virtualization
dev-tools
wanman: Multi-Agent Matrix for Claude Code and Codex
Local-mode multi-agent matrix framework that runs supervised Claude Code or Codex agents — coordinated through JSON-RPC, per-agent worktree isolation, and async message bus.
#github-trending#dev-tools#typescript
dev-tools
re_gent: Version Control for What Your AI Agent Actually Did
Version control purpose-built for AI coding agents — blame which prompt wrote any line, inspect full change context, and track every agent turn as a content-addressed step.
#github-trending#dev-tools#go
dev-tools
Stash: Persistent Memory for AI Agents Across Sessions
Persistent memory layer for AI agents across sessions — 9-stage consolidation turns observations into facts, relationships, patterns, and wisdom over time.
#github-trending#dev-tools#python
dev-tools
AWS Agent Toolkit for Coding Agents
AWS skills and MCP server for Claude Code, Codex, and Kiro — covers 300+ AWS services through CDK, CloudFormation, serverless, containers, and Bedrock agents.
#github-trending#dev-tools#aws
dev-tools
ktx: Context Layer for Data Agents
Self-improving context layer for data agents — ingests databases, BI tools, and wiki content; builds semantic layer with automatic fan/chasm trap resolution.
#github-trending#dev-tools#typescript
dev-tools
Knowhere: AI Document Memory for Agents
Ingest documents into persistent navigable memory — tree-like hierarchy reconstruction, multi-modal parsing, and agentic RAG with evidence-based citations.
#github-trending#dev-tools#python
dev-tools
AnySearch MCP Server: API Setup + Integrations for AI Agents
AnySearch MCP Server gives AI agents real-time web, finance, and academic search through one API key. Covers MCP, OpenAI functions, REST integrations, and Python setup in 10 min.
#github-trending#dev-tools#mcp
dev-tools
OpenPets: Desktop Pets for AI Coding Agents
Animated desktop pets that react to Claude Code, OpenCode, and MCP agents — privacy-safe reactions and speech without exposing code or secrets.
#github-trending#dev-tools#typescript
dev-tools
AgentMBOX – Pay-Per-Request Email for AI Agents
AI agents pay per email request via USDC on Solana or Base and get their own inbox with IMAP, SMTP, and REST API. No signup, no API keys — just @agentmbox.com.
#ai-agents#email#solana
dev-tools
Hopper - AI Agents for Mainframe Operations
Hopper connects AI agents to your mainframe through Model Context Protocol, enabling natural language operations and autonomous workflows on COBOL/Java systems.
#ai-agents#dev-tools#mainframe
dev-tools
Chamber - AI Teammate for GPU Infrastructure
AI agents that autonomously monitor, root-cause, and remediate GPU infrastructure issues. Reduce compute costs, improve GPU utilization, and accelerate ML research. YC W26.
#ai-agents#gpu#infrastructure
dev-tools
Runtime - Team-Wide AI Coding Agents Without the Chaos
Runtime gives your whole team safe access to Claude Code, Codex, and other coding agents with snapshot environments, scoped secrets, and infrastructure-level.
#ai-agents#developer-tools#coding-agents
review
BitBoard – AI Agents for Healthcare Back-Offices
AI agents that automate intake forms, chart prep, and referrals in healthcare clinics. HIPAA compliant with deterministic checks.
#ai-agents#healthcare#automation
dev-tools
Sim Studio – Visual Canvas for Building AI Agent Workflows
Sim Studio is a collaborative visual interface for building and deploying AI agent workflows. Design agents with a node-graph canvas, deploy as APIs, and.
#ai-agents#workflow-automation#visual-programming
dev-tools
Terminal Use - Filesystem-Based Agents for the Enterprise
YC W26 startup builds deployment infrastructure for sandboxed coding agents, research agents, and document processing tools that need filesystem access to work.
#yc-w26#ai-agents#dev-tools
dev-tools
Klaus – Hosted OpenClaw for Teams
Klaus runs OpenClaw—the 375k-star open-source AI agent—on a dedicated EC2 instance with pre-configured OAuth, automatic hotfixes via ClawBert AI SRE, and zero.
#openclaw#ai-agents#dev-tools
dev-tools
Shushu Internship Tool: JD to Interview AI Pipeline
Turn job descriptions into projects, projects into resumes, and resumes into interviews. AI-driven internship prep tool for CS students — from JD analysis to.
#github-trending#dev-tools#python
dev-tools
VibeCode Pro Max Kit: Context Memory for AI Agents
Spec-driven coding harness with self-improving context memory. 12 specialized agents, 32 skills — kills context rot and ships features instead of spaghetti.
#github-trending#dev-tools#javascript
dev-tools
Duel Agents: Adversarial AI Pair Programming Guide
CLI, SDK, and IDE plugins for adversarial AI agent workflows. Pit two AI agents against each other — one builds, one critiques — for higher-quality code.
#github-trending#dev-tools#typescript
ai-setup
Omnara – Remote Claude Code and Codex From Any Device
Omnara is a web and mobile agentic IDE that lets you run Claude Code and Codex sessions from anywhere. Keep your coding agents running even when you're away.
#ai-setup#dev-tools#ai-agents
dev-tools
Minicor – Windows Desktop RPA at Scale via MCP
Minicor connects AI agents like Claude Code and Codex to Windows virtual machines through an MCP server, enabling scalable desktop RPA with Python workflows.
#rpa#automation#windows
dev-tools
Ardent – Postgres Sandboxes in Seconds for Coding Agents
Ardent gives coding agents production-like Postgres sandboxes instantly, so they can test SQL safely without risking your actual database.
#database#dev-tools#ai-agents
dev-tools
Lucidic – AI Agent Debugging and Observability
Trace, debug, and evaluate AI agents in production with Lucidic's observability platform — one-line init, graph visualizations, and time-travel debugging.
#ai-agents#debugging#observability
dev-tools
Voygr – Maps API for AI Agents That Think Beyond Static Data
Voygr provides real-time place intelligence for AI agents—business validation, freshness signals, and web context that Google Maps APIs cannot surface.
#ai-agents#maps-api#dev-tools
dev-tools
Canary – AI QA Agent Tests PRs Against Real User Workflows
Canary reads your codebase, understands what a pull request changed, generates end-to-end tests for affected user flows, and runs them against preview apps.
#ai-qa#testing#developer-tools
dev-tools
Strata – MCP Server That Reveals AI Tools Step by Step
Strata is an open-source MCP server that reveals AI tools step-by-step as an agent works, instead of overwhelming it with thousands of tools at once.
#mcp#ai-agents#dev-tools
dev-tools
SourceTable Superagents – Spreadsheet Data Hub
SourceTable Superagents lets you connect any spreadsheet to external databases, REST APIs, or MCP servers — turning Excel into a universal data hub powered by.
#spreadsheet#data-integration#mcp
ai-setup
Sentrial – Catch AI Agent Failures Before Your Users Do
Sentrial monitors AI agents in production, detecting loops, hallucinations, and tool misuse the moment they happen. Here's how it works and how to set it up.
#ai-monitoring#ai-agents#dev-tools
dev-tools
Tabstack – Browser Infrastructure API for AI Agents
Mozilla-backed API that abstracts complex web browsing for AI agents—handles proxies, hydration, DOM parsing, and returns clean structured data instead of raw.
#ai-agents#browser-automation#dev-tools
dev-tools
Notte – Deterministic Browser Automation via Demonstration
Notte records your browser interactions once and compiles them into deterministic automation code — no LLM at runtime, no fragile selectors.
#browser-automation#ai-agents#dev-tools
ai-setup
Dedalus Labs – Full Linux Machines for AI Agents in 250ms
Dedalus Labs spins up persistent full Linux VMs for AI agents in under 250ms. No Dockerfiles, no YAML configs — just SSH, GPU, and a Python SDK.
#ai-agents#mcp#dev-tools
dev-tools
Propolis – Browser Agents That QA Your Web App Autonomously
Propolis runs swarms of AI browser agents that explore your web app, find bugs, and generate Playwright e2e tests for your CI pipeline. Here's how it works.
#browser-automation#qa#ai-agents
dev-tools
Hyperbrowser – Scalable Browser Infrastructure for AI Agents
Hyperbrowser spins up hundreds of headless browser sessions in secure isolated environments with sub-second launch times, captcha solving, and residential.
#browser-automation#ai-agents#web-scraping
ai-setup
Dedalus Labs – MCP Cloud Platform for Agentic AI Apps
Dedalus Labs connects any LLM to any MCP tool via a single OpenAI-compatible API endpoint. Upload MCP servers to the cloud, skip the Dockerfiles and YAML.
#mcp#ai-agents#dev-tools
dev-tools
Twill.ai – Cloud Agents That Auto-Submit PRs
Twill.ai is a YC S25 startup that lets you hand off coding tasks to cloud AI agents and get back finished pull requests on GitHub—no local setup required.
#ai-agents#github#developer-tools
dev-tools
Voker – Analytics for AI Agents
Voker is an agent analytics platform that gives engineering teams structured visibility into how their AI agents behave, perform, and cost — without digging.
#ai-agents#analytics#observability
ai-setup
Spine Swarm – Parallel AI Agents on a Visual Canvas
Spine Swarm runs parallel AI agents across 300+ models simultaneously, enabling research and client-ready deliverable creation through a visual canvas.
#ai-agents#multi-agent#dev-tools
review
Kita – VLM-Powered Credit Review Automation
Kita uses vision-language models to automate document-based credit review for lenders in emerging markets, parsing 50+ document types from PDFs to photos.
#fintech#ai-agents#document-ai
dev-tools
Smooth CLI – Give Your AI Agent a Browser That Works
Smooth CLI replaces low-level click/type/scroll with natural language commands. 20x faster, 5x cheaper, and works with Claude Code, OpenClaw, and any AI agent.
#browser-automation#ai-agents#cli-tools
ai-setup
Hyperbrowser – Scalable Browser Infrastructure for AI Agents
Cloud browsers built for AI agents that need to navigate, scrape, and interact with the web at scale. Handles proxies, stealth detection, and concurrent.
#browser-automation#ai-agents#infrastructure
ai-setup
Sentrial – Catch AI Agent Failures Before Your Users Do
YC W26-backed AI agent observability platform. Trace sessions, detect silent regressions, and A/B test prompts in production before failures reach users.
#ai-agents#observability#dev-tools
dev-tools
Superset – Orchestrate 100+ Coding Agents in Parallel
Superset runs Claude Code, Codex, Cursor, and other AI coding agents simultaneously in parallel workspaces. Orchestrate agents, automated workflows, and code.
#ai-agents#coding-agents#claude-code
dev-tools
AgentMesh – Define AI Agent Teams in YAML
Define multi-agent AI workflows in YAML and run them locally with one command. AgentMesh brings Docker Compose patterns to AI agent orchestration.
#ai-agents#multi-agent#mcp
dev-tools
Photo-agents Setup and Privacy Guide
Evaluate Photo-agents for image-agent workflows, including license keys, Python isolation, sample-image testing, metadata checks, and batch safety.
#github-trending#dev-tools#python
dev-tools
awesome-agentic-ai-zh Roadmap Guide
Explore awesome-agentic-ai-zh as a Chinese agentic AI learning roadmap, with setup notes, track selection, study workflow, and evaluation guidance.
#github-trending#dev-tools#python