AI agents directory for platform engineers: Connect with solutions by renowned AI agencies and automation experts.

AI Agents for platform engineers | AI Agent Store

thepopebot is an open-source template for deploying a 24/7 autonomous AI agent using GitHub Actions as the execution environment. You interact with the agent via Telegram (or a webhook). An event handler creates a job branch, GitHub Actions spins up a Docker container that runs the “Pi” coding agent, and the agent completes the task by committing changes and opening a pull request. Optional auto-merge workflows can merge results automatically. The project emphasizes security by filtering secrets at the process level so the agent cannot access them directly, and it treats the git repository history as the agent’s auditable, reversible memory.

thepopebot

Open-source autonomous coding agent that runs on GitHub Actions, does work in Docker, commits changes, and notifies you on Telegram.

ClawWatcher is a monitoring dashboard for OpenClaw that provides real-time visibility into what your agent is doing and what it costs. It focuses on cost transparency—tracking tokens (including input/output split), actions/tool calls, and dollars per task—so builders can identify inefficient prompts, expensive defaults, and workflows that burn budget unexpectedly. The product is positioned as a lightweight observability layer for OpenClaw usage and spend analysis to help teams reduce costs and debug agent behavior.

ClawWatcher

clawwatcher

Real-time OpenClaw monitoring that breaks down token spend, actions, and cost per task so you can spot waste and optimize prompts.

Tailscale is a secure connectivity platform that creates a private mesh network (“tailnet”) between devices and services using WireGuard as the data plane and a control plane for identity, key distribution, and policy. It’s commonly used by developers to give servers, containers, and services private, authenticated access without exposing ports publicly. For AI agent developers, it’s useful for securely connecting self-hosted agent runners, internal APIs, databases, vector stores, and automation tools across clouds and local machines. Tailscale includes features like ACL-based access policies, MagicDNS, device sharing, subnet routing, and exit nodes for routing traffic through a trusted device.

Tailscale

tailscale

Secure mesh VPN built on WireGuard for private access to devices and services, useful for self-hosted AI agent stacks and tooling.

Skill Scanner is an open-source security scanner for AI agent skills that helps developers and security teams assess whether a skill is safe to use. It detects threats such as prompt injection, data exfiltration attempts, and malicious code patterns by combining multiple analysis engines, including pattern-based detection (YAML + YARA), behavioral dataflow analysis, and LLM-assisted semantic review. It is designed for CI/CD usage and supports SARIF output for GitHub Code Scanning, enabling automated gating and actionable reports with file locations, severity, and remediation guidance. The project supports skill formats such as OpenAI Codex Skills and Cursor Agent Skills that follow the Agent Skills specification.

Skill Scanner

skill-scanner

Open-source security scanner for agent skills to detect prompt injection, data exfiltration, and malicious code patterns with SARIF output.

Amp is an agentic coding tool by Sourcegraph that runs in the terminal and editor extensions (including VS Code and compatible forks). It is designed for complex coding tasks such as multi-file edits, planning, and execution using multiple frontier model options. Amp includes a threads feature to save and share interactions, and offers “Amp Free” with a daily credit grant supported by sponsor ads, plus pay-as-you-go usage with no markup for individuals after the free allowance.

Agentic coding tool for terminal and editors that uses multiple frontier models, with a free $10/day grant and pay-as-you-go pricing.

Codiga (now part of Datadog) is a customizable static code analysis platform that runs in IDEs and CI/CD to detect code quality issues, security vulnerabilities, duplicated/complex code, and leaked secrets. It supports custom rules and rulesets created in a browser and can provide automated code reviews on platforms like GitHub/GitLab/Bitbucket, with fast feedback and automated fixes (“autofix”) directly in the developer workflow. Codiga also includes a separate “Coding Assistant” product focused on team code snippets and reusable patterns integrated into popular IDEs.

Codiga

codiga

Static code analysis and automated code reviews with IDE/CI integrations, security rulesets, custom rules, and one-click autofix.

New API is an open-source LLM gateway and AI interface management system that aggregates multiple AI providers behind a unified, OpenAI-compatible API. It supports format conversion (OpenAI/Claude/Gemini-style), model and channel management, weighted routing and failover, rate limiting and quotas, token-based access control, and API call auditing. The platform includes dashboards for usage and cost analytics, and exposes management and model APIs (chat, completions, embeddings, rerank, moderation, images, audio, and video) to simplify building applications that rely on multiple model vendors.

New API

new-api

Open-source LLM gateway that unifies OpenAI/Claude/Gemini-style APIs with routing, quotas, billing, auditing, and usage analytics.

CAST AI is an application performance automation platform for Kubernetes that helps teams reduce cloud spend and improve workload performance through automated optimization. It provides Kubernetes cost and performance monitoring, then adds automation such as intelligent autoscaling, rightsizing, bin packing, and Spot Instance orchestration with fallback to maintain reliability. CAST AI supports major managed Kubernetes services (EKS, GKE, AKS) and other environments, and offers usage-based plans with a free tier for monitoring plus paid tiers for automated optimization features.

CAST AI

cast-ai

Kubernetes automation platform that optimizes cost and performance with autoscaling, rightsizing, Spot automation, and monitoring.

CodeMender is a Google DeepMind research project focused on automatically improving software security by generating high-quality vulnerability patches. It’s designed to work both reactively (patching newly found vulnerabilities) and proactively (rewriting existing code to reduce or eliminate entire vulnerability classes). The agent leverages advanced “thinking” model capabilities plus a toolbox for reasoning and validation, including program analysis techniques (static and dynamic analysis, differential testing, fuzzing, SMT solvers) and multi-agent components for critique and regression checking. DeepMind reports that in the first six months of development it upstreamed dozens of security fixes to open-source projects, with all patches reviewed by humans before submission, and that broader availability is planned but not yet generally released.

CodeMender

codemender

Google DeepMind research AI agent that autonomously finds, patches, and validates fixes for software security vulnerabilities (human-reviewed before upstreaming).

x402 is an open, internet-native payment protocol that activates the long-reserved HTTP 402 “Payment Required” status code to handle payments directly inside web and API requests. It allows AI agents, apps, and APIs to charge and pay per request using stablecoins like USDC, removing the need for traditional API keys, subscriptions, or manual billing. Built as an open standard by Coinbase and deployed on chains such as Solana and Base, x402 supports low-cost, high-throughput micropayments suitable for agentic workflows, data APIs, model inference, and digital content. By embedding pricing, payment instructions, and proof of payment in normal HTTP flows, x402 enables fully autonomous, machine-to-machine commerce and a more granular, usage-based business model for online services.

x402 Protocol

x402-protocol

Open payment protocol that lets AI agents and APIs send instant stablecoin micropayments over HTTP using the 402 status code.

Reducto AI provides high-accuracy document ingestion APIs for AI teams. It parses complex PDFs, Excel, and PowerPoint, applies agentic OCR, splits multi-doc files, and extracts schema-precise fields. Reducto can summarize figures, convert graphs to tables, fill detected form fields, and output structured JSON suited for RAG and automation. Used across finance, healthcare, legal, and insurance, it offers SDKs/docs, a free tier, and enterprise security options.

Reducto AI

reducto-ai

Document intelligence API that parses, splits, OCRs, and extracts structured data from complex PDFs, slides, and spreadsheets.

Rasa is an open-source conversational AI framework for building contextual assistants in text and voice. Teams use Rasa Open Source for NLU, dialogue, and channel connectors, and scale with Rasa Pro and Rasa Studio for enterprise features like governance, analytics, and a no-code UI. The platform supports on-prem or cloud deployment, integrates with messaging/voice channels and backends, and emphasizes data control, reliability, and extensibility for production CX use cases.

Rasa

rasa

Open-source conversational AI framework with Pro & Studio tools to build secure, production-grade chat and voice assistants.