Tools

Cloud cost estimates for Terraform changes in pull requests

Infracost shows cloud cost changes directly in pull requests before infrastructure-as-code changes are deployed. It calculates cost impact across AWS, Azure, and GCP for Terraform, Terragrunt, CloudFormation, and AWS CDK workflows, with diffs in GitHub, GitLab, Bitbucket, and Azure DevOps. 12.4K+ GitHub stars, Apache 2.0 licensed. Used by GitLab, HelloFresh, JPMorgan Chase, BMW, and Accenture.

AI-powered API testing with traffic recording

Keploy is an open-source AI-powered testing platform that generates API, integration, and unit tests by recording real network traffic via eBPF. It captures API calls, database queries, and streaming events, then replays them as deterministic tests with auto-generated mocks — no code changes needed. Works across any language or framework with CI/CD pipeline integration and popular testing framework support including JUnit, PyTest, Jest, and Go-Test.

Run local LLMs with an intuitive desktop GUI and OpenAI-compatible API server.

Free desktop application by Element Labs for discovering, downloading, and running open-source LLMs locally. Features a curated Hugging Face model browser, side-by-side model comparison, parameter tuning, and an OpenAI-compatible API server on localhost:1234. Powered by llama.cpp with Metal acceleration for Apple Silicon.

AMD's open-source local LLM server with GPU and NPU acceleration

Lemonade is AMD's open-source local AI serving platform for LLMs, image generation, speech recognition, and text-to-speech on your own hardware. Built in lightweight C++, it can detect CPU, GPU, and NPU backends and is extra optimized for Ryzen AI, Radeon, and Strix Halo PCs. Lemonade exposes OpenAI, Anthropic, and Ollama-compatible APIs, ships with a desktop model manager, and supports source-confirmed GGUF, FLM, and ONNX models across Windows, Linux, macOS, and Docker.

Open-source platform for the complete machine learning lifecycle.

MLflow is an open-source platform for managing the end-to-end machine learning lifecycle. Covers experiment tracking, model packaging, model registry, and deployment. Created by Databricks and now a Linux Foundation project. Integrates with TensorFlow, PyTorch, scikit-learn, Hugging Face, and all major ML frameworks.

GPU-accelerated open-source vector database

Milvus is an open-source vector database with 45K+ GitHub stars for billion-scale similarity search. Features GPU-accelerated indexing, hybrid search combining vector and scalar filtering, multi-tenancy, partitioning, and horizontal scaling. Supports HNSW, IVF, DiskANN, and GPU index types. SDKs for Python, Java, Go, and Node.js. Zilliz Cloud offers a managed version. A production-grade foundation for RAG pipelines and recommendation systems at enterprise scale.

Minimal terminal coding harness

Pi Coding Agent is an MIT-licensed Node.js CLI from earendil-works for building and running coding agents in a local terminal. The current package describes a read/bash/edit/write toolset and session management, while the repo positions Pi as a unified LLM API, agent loop, TUI, and coding-agent CLI. It is best framed as a lean, self-extensible BYO-model toolkit rather than a managed IDE.

Open-source terminal AI agent by Alibaba

Apache-2.0 terminal coding agent with Qwen, OpenAI, Anthropic, Gemini, third-party, and local-model support. Qwen OAuth free access ended on April 15, 2026; use Alibaba ModelStudio, a provider API key, or a self-hosted endpoint.

Infrastructure, instantly

Modern cloud platform for deploying full-stack apps, databases, and workers with instant provisioning and usage-based pricing. Deploy from GitHub or CLI with zero config for Node.js, Python, Go, Rust, and Docker. Built-in PostgreSQL, MySQL, Redis, and MongoDB with auto backups. Features private networking, environment management, cron jobs, TCP proxying, and real-time logs. Popular with indie hackers and startups for fast MVPs with a generous free trial including $5 monthly credits.

Always-on cloud engineer that lives in Slack and ships verified PRs

Roomote is a Slack-first cloud coding agent from RooCodeInc that takes prompts end-to-end across GitHub, Linear, Notion, Sentry, and your own dev environment, then opens self-verified pull requests for review. It is the team behind 24K+ star Roo Code going all-in on cloud agents: mention it in Slack, let it run in an isolated environment, and review the PR through your normal GitHub flow.

Privacy-first open-source web analytics with session replays

Rybbit is an open-source, privacy-friendly alternative to Google Analytics with real-time dashboards, session replays, funnels, journeys, Web Vitals, retention, custom events, and error tracking. It uses a cookieless model, is AGPL-3.0 for self-hosting, and now uses rybbit.com as its canonical public site.

Autonomous AI pentester for web apps and APIs

Shannon is an autonomous white-box AI pentesting tool for web applications and APIs. It analyzes authorized source code, identifies attack vectors, attempts proof-by-exploitation, and produces remediation-ready reports. Shannon Lite is AGPL-3.0 for local use, while Shannon Pro is the commercial Keygraph platform for continuous security testing.

Code intelligence platform

Code intelligence platform providing universal code search across all repositories, languages, and code hosts. Search with regex, structural patterns, and diff/commit search across GitHub, GitLab, Bitbucket, and self-hosted repos. Features code navigation (go-to-definition, find references) in the browser, batch changes for large-scale refactoring, code insights for tracking metrics, and Cody AI assistant for code generation and explanation. Self-hosted and cloud options.

OpenTelemetry-native observability with AI tracing, logs, traces, metrics, and session replay — self-hosted in 90 seconds.

Traceway is an open-source, OpenTelemetry-native observability platform that combines logs, traces, metrics, exceptions, session replay, and AI tracing in a single self-hosted system. MIT licensed with no open-core restrictions, it deploys in 90 seconds via Docker Compose and accepts OTLP/HTTP from any OTel SDK without a Collector or per-language vendor SDK.

Turn scripts into workflows, UIs, and APIs at scale

Windmill is an open-source workflow engine and developer platform built in Rust that turns scripts in Python, TypeScript, Go, Bash, SQL, and other languages into auto-generated UIs, API endpoints, workflows, data pipelines, AI agents, and scheduled jobs. The project publishes performance benchmarks against Airflow/Prefect/Temporal, supports Docker/Kubernetes self-hosting, and offers paid enterprise features.

Enterprise SSO and directory sync APIs for SaaS applications

WorkOS provides B2B identity infrastructure for SaaS teams that need AuthKit user management, Enterprise SSO, Directory Sync, Admin Portal, audit logs, RBAC/FGA, Radar, and MCP Auth without building every identity integration themselves. It is strongest when enterprise customers require SAML/OIDC, SCIM provisioning, and organization-level auth workflows.

Accessibility-tree desktop automation engine for deterministic native-app control

agent-desktop is a Rust-native desktop automation engine for AI agents that need structured control of native applications without relying only on screenshots or pixel loops. It exposes accessibility-tree snapshots, stable element references, progressive traversal, and action primitives that can let coding agents and automation stacks operate on Windows, macOS, Electron, and legacy interfaces with lower token cost and better repeatability than pure vision control.

Go implementation of the Model Context Protocol SDK

mcp-go is a Go implementation of the Model Context Protocol, providing both server and client SDKs for building MCP integrations in Go. It supports stdio and SSE transports, resource management, tool registration, and prompt templates. Designed for Go developers building MCP servers for DevOps tools, CLI applications, and backend services. Over 8,000 GitHub stars.

DiskANN-powered vector search extension for PostgreSQL

pgvectorscale is an open-source PostgreSQL extension from Timescale that complements pgvector with DiskANN-based approximate vector search. It is useful for teams that want faster embedding retrieval while keeping vectors, filters, and application data inside the Postgres ecosystem instead of adopting a separate hosted vector database.

AI pair programming in your terminal

Terminal-based AI pair programmer with deep git integration. Auto-commits changes with meaningful messages and creates repository maps for navigating large codebases. Works with Claude, GPT, DeepSeek, and local models. One of the most popular open-source AI coding tools, known for its reliability, broad model support, and seamless command-line workflow.

Build and deploy AI chatbots and agents visually

Botpress is a conversational AI platform founded in 2017 that combines a visual Agent Studio with LLM-native architecture for building chatbots and autonomous agents. It offers a drag-and-drop flow builder, knowledge base indexing from documents and websites, an Autonomous Engine for generative AI workflows, and deployment across web chat, WhatsApp, Telegram, Slack, and other channels. Botpress runs as a cloud SaaS or self-hosted via Docker with pricing starting at $0/month pay-as-you-go.

Cloud browser automation via MCP for scalable testing

Browserbase MCP Server gives MCP clients a hosted or self-hostable browser through Browserbase and Stagehand. It exposes tools for starting sessions, navigating, acting, observing, extracting, and taking screenshots, with a hosted Streamable HTTP endpoint for easiest setup and local STDIO/Docker options for teams that want to run the Apache-licensed server themselves.

AI code review by Cursor with multi-pass parallel analysis

BugBot is Cursor's AI pull request review layer for teams that want automated PR comments, custom rules, learned repository standards, and agent-assisted fixes close to their coding environment. Current docs list GitHub, GitHub Enterprise Server, GitLab, GitLab Self-Hosted, and Bitbucket Cloud setup paths. Pricing is usage-based, so Cursor-heavy teams should manage effort levels, privacy/storage settings, and review spend.

Git-native AI agent session capture and reasoning traceability

Checkpoints by Entire captures the full reasoning context behind AI-generated code directly in Git. Entire records transcripts, prompts, files touched, token usage, and tool calls alongside every commit. Session metadata lives on a separate branch keeping your history clean, with rewind capabilities to restore any previous agent checkpoint when things go sideways.

Free AI code completion supporting 70+ languages

AI-native code editor (now operating as Windsurf) built on VS Code with the Cascade agentic assistant for multi-file editing, terminal execution, and codebase-wide context. Codeium supports 70+ programming languages with lightning-fast completion, Cascade Memories for customizable AI behavior, semantic indexing, and automatic linter-error fixes — combining completion plus full agent in one cohesive IDE.

Source-available LLM app development platform

Source-available LLM application development platform combining a visual no-code canvas with backend capabilities for building AI workflows, RAG pipelines, and agent systems from prototype to production. Integrates hundreds of models from dozens of providers, with PDF/PPT ingestion, ReAct agents with 50+ tool integrations, and multi-step orchestration. Used by both technical and non-technical teams to ship GenAI apps like chatbots and Q&A systems.

Context compression for LLM apps and coding agents

Headroom is an Apache-2.0 context compression layer for LLM apps and coding agents. It compresses tool output, logs, files, RAG chunks, and agent history through a local library, proxy, wrapper, or MCP server, with retrieval hooks for bringing originals back when needed. Treat its savings numbers as Headroom-reported benchmarks, not independent aicoolies measurements.

HyperDX is the ClickStack UI for ClickHouse-backed observability. It provides a frontend for exploring logs, traces, metrics, session replay, dashboards, and alerts, with an OpenTelemetry-centered deployment path for teams that want a self-hosted or ClickHouse-aligned observability stack.

Google async coding agent for GitHub tasks, plans, and PRs

Jules is Google's async coding agent for GitHub repositories. Users start work from a prompt, GitHub issue label, scheduled task, or opt-in Suggested Task; Jules runs in a Google Cloud VM, proposes a plan, and opens PR-ready diffs. Free Jules offers 15 tasks/day and 3 concurrent tasks on Gemini 2.5 Pro; Pro/Ultra raise limits and start with Gemini 3 Pro access.

Knowledge graph-powered RAG framework from HKU

LightRAG is a research-backed RAG framework from Hong Kong University that combines knowledge graph structures with vector search for more contextual retrieval. Published at EMNLP 2025, it extracts entities and relationships from documents to build a structured knowledge graph, then uses dual-level retrieval across both graph and vector representations with five query modes: naive, local, global, hybrid, and mix.

Web platform for modern development

Jamstack-focused cloud platform specializing in deploying static sites, serverless functions, and modern web applications with Git-based CI/CD. Features instant rollbacks, deploy previews for every PR, split testing, edge functions, form handling, identity/auth, and a global CDN with automatic HTTPS. Native support for Next.js, Nuxt, Gatsby, Hugo, Astro, and all major static site generators. Free $0 forever plan plus Personal and Pro credit-based tiers for growing traffic and team workflows.

Full-stack observability with AI-powered monitoring

New Relic is a full-stack observability platform combining APM, infrastructure monitoring, logs, traces, browser/mobile monitoring, synthetics, and AIOps. Current public copy highlights 50+ capabilities, 100 GB/month free data ingest, one free full platform user, unlimited basic users, and 800+ pre-built integrations.

Open-source AI coding agent for the terminal

Open-source terminal-based AI coding agent built in Go by the SST team, with a rich TUI (Bubble Tea) supporting 75+ model providers including OpenAI, Anthropic, Gemini, Bedrock, Groq, and OpenRouter. Features vim-like editing, persistent SQLite sessions, and LSP integration for 40+ languages. Fully free with no vendor lock-in, it has rapidly grown to 95k+ GitHub stars.

Open-source Terraform fork — community-driven Infrastructure as Code.

OpenTofu is an open-source fork of Terraform created by the Linux Foundation after HashiCorp switched Terraform to the BSL license. Designed to preserve existing Terraform workflows and configurations, it offers state encryption, early variable evaluation, and a community-driven development model. Backed by major cloud providers and companies.

One tool for intercepting, mocking, and replaying HTTP — acquired by BrowserStack

Requestly is a BrowserStack-backed API client, HTTP interceptor, mock server, and session replay tool for frontend and QA teams. Its current product is commercial/API-client led, while the legacy interceptor/open-source code is AGPLv3. The free plan covers individual workflows, and Pro lists at $12/user/month monthly or $9/user/month annually for collaborative QA and frontend debugging teams.

24/7 local screen & audio recording for AI agents

Screenpipe is an open-source Rust platform that records your screen and microphone 24/7 locally, then lets AI agents automate tasks based on what you've done. It uses event-driven capture with OS accessibility trees for efficient text extraction, stores everything in local SQLite, and exposes a REST API plus MCP server for AI integration with Claude, Cursor, and Ollama.

Managed SonarQube Cloud code quality and security analysis for CI/CD workflows.

SonarQube Cloud, still commonly associated with the SonarCloud name, is SonarSource’s managed code quality and security SaaS for GitHub, GitLab, Bitbucket, and Azure DevOps. It scans pull requests for bugs, vulnerabilities, security hotspots, code smells, duplication, and coverage regressions, then enforces Quality Gates without running SonarQube Server. Current Sonar docs frame the cloud service around 40+ languages, with Team from $32 monthly and Enterprise custom.

LLM evaluation and tracking with RAG triad metrics

TruLens is an open-source framework for evaluating and tracking LLM experiments with feedback functions, RAG triad metrics (answer relevance, context relevance, groundedness), and Honest/Harmless/Helpful evaluations. Features a unified Metric API for systematic evaluation of RAG pipelines and AI agents. 3,200+ GitHub stars, MIT licensed. Snowflake partnership adds enterprise integration. Supports LangChain, LlamaIndex, and custom LLM applications.

Cross-agent messaging for CLI coding agents

agmsg is an MIT-licensed Bash and SQLite messaging layer for CLI coding agents. It lets Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Antigravity, OpenCode, Hermes, and other terminal agents exchange messages through a shared local database instead of relying on a human copy-paste relay. It is intentionally not MCP, not a broker, and not a subagent framework.

MCP, ACP and Skills support for building production coding agents — interactive or automated.

fast-agent is an Apache-licensed Python framework for building and running LLM agents with full MCP (Model Context Protocol) and ACP support. It ships with an interactive shell mode, Skills management, and multi-model routing — making it a practical platform for coding agents, workflow automation, and agent evaluation across Claude, Codex, HuggingFace, and local models.

Google’s open-source Kubernetes assistant that translates natural-language intent into precise cluster operations.

kubectl-ai is an AI-powered Kubernetes assistant from Google Cloud Platform. It acts as an intelligent interface for cluster work, translating operator intent into Kubernetes commands and workflows. The key distinction from reactive diagnosis tools is that kubectl-ai is designed as an interactive natural-language interface for planning and executing Kubernetes operations, with provider configuration and MCP-oriented workflows around the CLI.

Serverless vector and full-text search on object storage

turbopuffer is a serverless vector and full-text search engine built on object storage and vendor-positioned as roughly 10x cheaper than traditional vector databases. Used by Anthropic, Cursor, Notion, and Atlassian for production search workloads. Official site reports 4T+ documents, 10M+ writes/s, and 25k+ queries/s in production systems. Funded by Thrive Capital.

Lightweight multi-modal agent framework

Fast, lightweight Python framework for building multi-modal AI agents, formerly known as Phidata. Includes built-in memory, knowledge bases, tools, and reasoning capabilities with 40K+ GitHub stars. Designed for developers who want to build production-ready agents quickly with minimal boilerplate, supporting structured outputs and multi-agent coordination out of the box.

AWS AI coding assistant with code generation and security scanning

AI coding assistant from AWS with inline code suggestions, chat, code transformation, and built-in security vulnerability scanning. Deep integration with AWS services and CLI makes it particularly powerful for cloud-native development. Helps developers modernize legacy code, optimize AWS resource usage, and implement security best practices across their entire development workflow.

Open-source backend-as-a-service platform

Appwrite is an open-source BaaS platform with 56K+ GitHub stars providing authentication, databases, storage, functions, messaging, and real-time APIs out of the box. Self-hostable alternative to Firebase with 15+ client and server SDKs. Features OAuth login with 30+ providers, document-based database with queries, file storage with image transforms, serverless functions, and push notifications. Docker-based deployment with a web console for management.

Terraform pull request automation via GitHub/GitLab comments

Atlantis is a self-hosted Terraform pull request automation tool that runs plan and apply operations triggered by GitHub, GitLab, Bitbucket, or Azure DevOps comments. Type 'atlantis plan' on a PR to see infrastructure changes, then 'atlantis apply' to deploy. 9,100+ GitHub stars, Apache 2.0 licensed. Widely adopted as the standard for GitOps-style Terraform workflows, with locking to prevent concurrent modifications to the same resources.

Desktop app for running AI coding agents in parallel

Baton is a desktop application for running multiple AI coding agents in parallel inside isolated git worktrees. It supports Claude Code, Codex CLI, OpenCode, Gemini CLI, visual diffs, status notifications, MCP server support, built-in Git operations, and one-click PRs to GitHub or GitLab.

Telemetry-aware AI code reviewer that checks how pull requests may affect real services.

Baz is an AI code-review platform focused on production-aware pull requests. Instead of only reading the diff, Baz connects code changes to application telemetry so reviewers can understand what endpoints, services, and runtime behavior may be affected. That makes it a useful complement to existing AI PR bots when the question is not just whether a change looks correct, but whether it could break a live system.