Agenta delivers a comprehensive open-source LLMOps workspace that covers the full lifecycle of AI application development — from prompt engineering through production monitoring. The platform supports 15+ model providers including OpenAI, Anthropic, Google Gemini, Mistral, Groq, Together AI, Azure, AWS Bedrock, and self-hosted models via Ollama, enabling teams to switch between providers without code changes. The prompt playground allows side-by-side comparison of different configurations, while the evaluation system offers LLM-as-a-Judge assessment, 20+ pre-built evaluators covering semantic similarity, regex matching, and factual accuracy, plus custom Python evaluators for domain-specific requirements. Teams run evaluations through both the web UI for subject matter experts and the Evaluation SDK for programmatic CI/CD integration. The observability layer captures full trace visibility across complex agentic workflows, flagging quality issues like hallucinations and off-topic responses in real time. Human annotation workflows let domain experts review and annotate LLM outputs, feeding corrections back into the evaluation loop. The architecture supports Chain of Prompts, RAG pipelines, and multi-step agent workflows, integrating with frameworks like LangChain and LlamaIndex. Self-hosting deploys via Docker Compose with Traefik for routing, requiring only a clone, environment configuration, and a single docker compose command. On RepoCloud, deploy Agenta on a dedicated VPS with root SSH access, persistent storage for evaluation datasets and traces, and complete control over model provider credentials, all under the MIT license with no usage restrictions.

With 12,600 GitHub stars and 52 releases in under a year of development, InsForge is the fastest-growing open-source backend platform purpose-built for AI coding agents — giving Claude, Cursor, and any MCP-compatible tool direct access to database, authentication, storage, compute, and AI model infrastructure through a single self-hosted stack. The native MCP server exposes every InsForge operation as callable tools, letting coding agents autonomously create database tables, manage user authentication, upload files, deploy edge functions, and ship complete full-stack applications without human intervention. The Model Gateway provides an OpenAI-compatible API that routes requests across multiple LLM providers (OpenAI, Anthropic, Google, and open-source models) with unified billing, rate limiting, and fallback logic. PostgreSQL with pgvector handles both relational data and vector embeddings for RAG pipelines, while S3-compatible storage manages file uploads and static assets. Edge Functions run serverless TypeScript code on Deno with sub-millisecond cold starts for API endpoints, webhooks, and scheduled tasks. The authentication system provides user management, OAuth2 flows, sessions, and magic links with JWT token handling built in. Site Deployment builds and serves frontend applications with automatic SSL and custom domain configuration. The CLI paired with Agent Skills enables terminal-based workflows where agents invoke InsForge operations directly from the command line. Deploy via Docker with PostgreSQL as the only required external dependency. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Super Productivity eliminates the context switching between issue trackers, calendars, and timer apps that fragments developer focus, pulling tasks from Jira, GitHub, GitLab, Gitea, OpenProject, Linear, ClickUp, Trello, and Azure DevOps into one local-first interface. With 21,000+ stars and availability across web, desktop, Android, and iOS, it syncs issue status, subtasks, and time logs bidirectionally so sprint planning and worklog submission happen without leaving the app. CalDAV integration pulls calendar events into your task timeline for visual timeboxing. Built-in Pomodoro and Flowmodoro timers enforce focused intervals with configurable break schedules. Data stays under your control in browser IndexedDB by default, with optional AES-encrypted sync via WebDAV, Nextcloud, Dropbox, or the SuperSync server ensuring no task data touches infrastructure you do not own. The extensible plugin system supports JavaScript-based custom panels, automations, and MCP plugins for AI workflows. A REST API on port 3876 enables external script integration for desktop automation. Time tracking generates exportable timesheets compatible with corporate reporting systems. The Docker container serves the Angular PWA through Nginx on port 80, consuming roughly 50 MB of RAM. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

TencentDB Agent Memory provides a team-level memory hub that transforms AI agent conversations, documents, and codebases into four governed, shareable memory assets: Chat Memory for conversation history, Skills extracted from completed tasks, LLM-Wiki built from document ingestion, and Code-Graph generated from codebase analysis. The four-tier semantic pyramid structures long-term memory from L0 raw conversation capture through L1 episodic extraction and L2 scenario aggregation to L3 persona synthesis, enabling hierarchical drill-down via node and result references instead of flat vector recall. The Node.js Gateway sidecar handles capture, extraction, storage, recall, and pipeline scheduling through RESTful HTTP v2 endpoints on port 8420, while the Memory Proxy intercepts Anthropic-format API calls to inject team memory context into Claude Code, CodeBuddy, and other coding agents transparently. Local SQLite with the sqlite-vec extension provides the default storage backend with hybrid BM25 keyword plus vector embedding plus reciprocal rank fusion retrieval requiring zero external API dependencies. Teams manage ownership, versions, status, visibility, usage counts, and agent bindings through the Memory Hub dashboard with role-based access control separating System Admin and team-level Admin and Member permissions. Official TypeScript and Python SDKs provide programmatic access for custom framework integration beyond the built-in OpenClaw plugin and Hermes Agent adapter. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Used by Tailwind Labs and recognized as an official GitHub funding partner, Polar is the open-source billing infrastructure that lets developers ship production-ready monetization in hours instead of weeks. Meter tokens, API calls, agent runs, GPU seconds, and storage with event-level precision, then compose usage billing with subscriptions, seats, credits, trials, and discounts into whatever pricing model your product requires. As Merchant of Record, Polar handles sales tax, VAT, chargebacks, receipts, and regulatory compliance across all supported countries so you receive clean payouts without building tax infrastructure. Integrate via the full REST API with official SDKs for JavaScript, Python, PHP, and Go, plus framework adapters for Next.js, Astro, Remix, SvelteKit, and Laravel enabling checkout integration in minutes. Automatically deliver benefits upon purchase including GitHub repository access, Discord roles, license keys, file downloads, and meter credits through configurable automation rules. The built-in customer portal provides subscription management, payment method updates, invoice history, and benefit access with full white-label branding. Monitor revenue, costs, and margins through real-time analytics dashboards showing the unit economics every AI startup needs to scale. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache License 2.0 licensed.

Trusted by over seven million developers worldwide with 310+ contributors and more than 10,600 GitHub stars since 2011, SonarQube has become the industry standard for automated code review and continuous code quality inspection. The platform performs deep static analysis across Java, JavaScript, TypeScript, Python, C#, C++, PHP, Kotlin, Go, Ruby, Swift, and 30+ additional languages, detecting bugs that cause runtime failures, security vulnerabilities exploitable by attackers, security hotspots requiring manual review, code smells degrading maintainability, and code duplications increasing technical debt. Quality Gates define pass-fail thresholds on metrics like coverage, duplications, reliability rating, and security rating, failing CI/CD pipelines when new code introduces issues below organizational standards. Pull request analysis decorates GitHub, GitLab, Bitbucket, and Azure DevOps merge requests with inline issue annotations and overall quality summaries before merging. Built-in quality profiles provide curated rule sets per language following the Sonar Way methodology, with dedicated profiles for AI-generated code that target patterns commonly introduced by agentic coding workflows. Infrastructure-as-Code analysis covers Terraform, Kubernetes, Docker, Ansible, CloudFormation, and Helm charts with supply-chain security rules for CI/CD pipelines. The companion IDE plugin delivers real-time analysis with quick-fix guidance directly in VS Code, IntelliJ, and Eclipse. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. LGPL-3.0 licensed.

With nearly 5,000 GitHub stars earned in under two years, WhoDB has rapidly emerged as the lightweight alternative to heavyweight database clients like DBeaver and DataGrip by delivering a sub-50MB binary that starts in under a second and connects to 18+ database systems from a single interface. The Go backend serves the React and TypeScript frontend with table virtualization for efficient rendering of large result sets, lazy loading, and query result streaming that keeps the interface responsive even when browsing tables with millions of rows. The Community Edition connects to PostgreSQL, CockroachDB, YugabyteDB, MySQL, MariaDB, TiDB, SQLite, DuckDB, MongoDB, FerretDB, Redis, Valkey, Dragonfly, Elasticsearch, OpenSearch, ClickHouse, QuestDB, and Memcached through a unified credential selector that switches between databases with minimal configuration. Interactive schema diagrams render entity-relationship graphs showing table structures, foreign keys, and column types for visual database exploration. The Jupyter-style query scratchpad provides SQL autocomplete, syntax highlighting, and multi-statement execution with paginated results. AI integration optionally connects to Ollama, OpenAI, Anthropic, LM Studio, or any OpenAI-compatible provider for natural language database queries — ask questions in plain English and receive generated SQL. Data management includes inline row editing, CSV export, and filtered data views. Docker deployment runs a single container exposing port 8080. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Kodus AI automates pull request code review with inline AI comments across GitHub, GitLab, Bitbucket, and Azure DevOps, supporting any LLM provider at cost with zero token markup. The multi-service TypeScript architecture deploys via Docker Compose, running an API server, background worker, webhooks service, and React dashboard backed by PostgreSQL with pgvector, MongoDB, and RabbitMQ. Integration covers both cloud platforms and their enterprise flavors (GitHub Enterprise Server, GitLab Self-Managed, Bitbucket Data Center) using standard OAuth flows and webhook signing to keep the review loop entirely inside your network. The platform is model-agnostic with Bring Your Own Key support for Claude, GPT, Gemini, Llama, and any OpenAI-compatible endpoint including locally-hosted models. Custom review rules combine your team's coding standards with requirements pulled from Jira, Linear, and Notion, automatically checking every PR against documented specifications. The CLI enables local reviews against working trees, staged diffs, branches, or specific commits, integrating into CI/CD pipelines as pre-merge gates. Source code is never stored and never used for model training, with all data encrypted in transit and at rest. 1,270+ stars and 129+ releases since March 2025. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

With over 126,000 GitHub stars and adoption across professional studios, research labs, and independent creators, ComfyUI has become the most widely used node-based interface for generative AI workflows — supporting image, video, audio, and 3D content creation through a single visual canvas. The graph editor natively supports Stable Diffusion 1.5, SDXL, SD3.5, Flux.1, Flux.2, HunyuanDiT, Lumina Image 2.0, HiDream, Qwen Image, and Pixart for image generation, plus Wan 2.1 and 2.2, LTX-Video, HunyuanVideo 1.5, CogVideoX, and Mochi for video, ACE-Step and Stable Audio for audio, and Hunyuan3D 2.0 for 3D models. Built-in tools handle inpainting, outpainting, ControlNet conditioning, LoRA and Hypernetwork loading, ESRGAN upscaling, area composition, model merging, and GLIGEN spatial control without writing code. The execution engine implements asynchronous queue processing with partial graph re-execution, running only changed nodes between iterations, and smart VRAM management that offloads models on GPUs with as little as 1 GB of memory. API nodes optionally connect to closed-source models through Comfy API while the core runs fully offline. Reusable subgraphs and App Mode expose complex workflows as simplified interfaces for non-technical users. The V3 custom node schema enables stateless execution with async support and process isolation. The TypeScript and Vue frontend ships as a PyPI package with stable releases every two weeks. Workflows save as JSON and embed in generated PNG, WebP, and FLAC files for reproducibility. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL v3.0 licensed.

With 5,600+ GitHub stars and deep dbt integration, Lightdash is the open-source Agentic BI platform that treats analytics like software — defining metrics, dimensions, joins, permissions, and caching in a governed context layer that powers dashboards, AI agents, data apps, embedded analytics, and MCP server endpoints simultaneously. The dbt Write-Back feature lets business users create custom metrics and models in the UI, then automatically generates pull requests in GitHub or GitLab so every change flows through code review and CI validation before reaching production. Context-specific AI analysts automatically select relevant models and metrics, build queries, and present insights in plain English, while row-level security, user attributes, and customer-facing permissions ensure data governance at every layer. The platform connects to BigQuery, Snowflake, Redshift, Databricks, PostgreSQL, Trino, and ClickHouse through warehouse adapters, with the TypeScript monorepo built on React, Mantine, Vite, and TanStack Query on the frontend plus Node.js, Express, Knex, and PostgreSQL on the backend. Data teams build analytics with coding agents, preview changes from the CLI, validate in CI pipelines, and review charts and dashboards in pull requests — making the entire analytics lifecycle version-controlled and reproducible. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

RAGFlow has established itself as one of the most widely adopted open-source RAG engines available, powering production AI systems that demand traceable, hallucination-free answers from complex enterprise data. The platform processes PDF, DOCX, Excel, and PPT files through vision-based deep document understanding with layout analysis and OCR, extracting structured knowledge from tables, charts, and images that simpler parsers miss entirely. RAGFlow's hybrid retrieval pipeline combines vector search with BM25 keyword matching and multi-stage reranking across configurable document stores including Elasticsearch, InfiniFlow's Infinity engine, OpenSearch, and OceanBase. Developers connect any combination of LLM providers — OpenAI, DeepSeek, Anthropic Claude, Google Gemini, and locally-hosted models via Ollama — through a unified configuration layer. The visual agent workflow system enables multi-step reasoning chains with persistent memory, tool calling, and pre-built templates for common enterprise scenarios. RAGFlow synchronizes data from Confluence, S3, Notion, and Google Drive, and delivers answers through chat integrations with Feishu, Discord, Telegram, and Line. The Python SDK and RESTful API on port 9380 provide programmatic access to knowledge base management, document parsing, and conversational retrieval. The full stack deploys via Docker Compose with MySQL for metadata, Redis for task orchestration, and MinIO for object storage. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Livebook is an interactive notebook for Elixir where you write code alongside rich Markdown prose, execute it cell by cell with reactive dependency tracking, and deploy finished notebooks as standalone web applications with a single click. Nearly 6,000 GitHub stars reflect the Elixir core team's investment in a platform where code cells run on demand alongside Mermaid diagrams and KaTeX mathematical formulas. The Kino visualization library renders Vega-Lite charts, interactive data tables with sorting and pagination, Leaflet maps, and Mermaid diagrams directly within notebook output cells, while custom Kino components enable building interactive controls with sliders, text inputs, and buttons that feed values back into running code. Smart cells abstract high-level tasks into configurable UI widgets: query PostgreSQL, MySQL, SQLite, and BigQuery databases, train machine learning models with Axon, plot charts, and build map visualizations without writing boilerplate code. Real-time collaboration lets multiple users edit the same notebook simultaneously with cursor presence indicators and synchronized cell evaluation. Notebooks are stored as .livemd files, a Markdown-compatible format that renders cleanly on GitHub and integrates with standard version control workflows. Custom runtimes connect Livebook to existing Elixir applications for live introspection and documentation of running systems. The Docker image at ghcr.io/livebook-dev/livebook exposes ports 8080 and 8081 with password or token authentication. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Reaching 45,000 GitHub stars within seven months of launch, Multica is the fastest-growing open-source platform for managing AI coding agents as first-class teammates — assign an issue to Claude Code, Codex, Cursor, Copilot, Kimi, or any of 21 supported agent CLIs and it picks up the work, comments progress in real time via WebSocket, raises blockers, and hands the result back for human review before anything merges. The Go backend (Chi router, sqlc-generated type-safe queries, gorilla/websocket) connects to PostgreSQL 17 with pgvector for semantic search across workspace history, while the Next.js 16 App Router frontend delivers workspace dashboards showing per-agent token spend, execution time, daily cost charts, and runtime status across unlimited connected machines. Agent Skills provide reusable methods, reference material, and supporting files that compound across runs — a persistent knowledge layer that makes each subsequent task faster and more accurate. Squads let a leader agent select the right specialist for subtasks, creating multi-agent workflows without manual orchestration. Review gates ensure no AI-generated code ships to main without explicit human approval. Self-host via Docker Compose or Kubernetes with full Git integration across GitHub, GitLab, Gitea, and Forgejo including self-hosted instances. The CLI and REST API make every surface scriptable, and Autopilot automations trigger agent runs from events. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed with additional conditions.

With over 48,000 GitHub stars and monthly releases since March 2023, LocalAI is the self-hosted AI engine that replaces every OpenAI endpoint with a single Docker container running on your own infrastructure — serving chat completions, image generation, text-to-speech, speech-to-text, embeddings, vision, video generation, and function calling through identical API schemas that require zero application code changes. The composable backend architecture isolates each inference engine as a separate gRPC service running in its own OCI container, so llama.cpp, vLLM, SGLang, transformers, whisper.cpp, diffusers, MLX, Stable Diffusion, and Flux install on demand without touching the core, can run on separate machines, and a fault in one never affects others. Hardware acceleration spans NVIDIA CUDA 12 and 13, AMD ROCm, Intel oneAPI/SYCL, Apple Silicon Metal, Vulkan, and NVIDIA Jetson L4T — or runs entirely on CPU without any GPU. Built-in AI agents support autonomous tool use, retrieval-augmented generation, Model Context Protocol integration, and skill-based workflows directly in the web interface. The model gallery provides curated YAML configuration files for hundreds of models that install with a single command, while P2P federated inference distributes model shards across multiple machines for running models larger than any single node's memory. Multi-user API key authentication with quotas and role-based access enables team deployments. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Hyperswitch from Juspay delivers the most comprehensive open-source payment orchestration stack available — a Rust-built platform that connects to Stripe, Adyen, Braintree, Worldpay, Checkout.com, Cybersource, and 120+ payment processors through a single API integration. Intelligent routing drives each transaction to the processor with the highest predicted authorization rate using rule-based, volume-based, and machine learning algorithms, while seamless failover and automatic retries recover revenue from declined transactions using 30+ parameters including decline codes, card BIN, transaction size, and region. The PCI-compliant card vault stores payment methods securely in a dedicated service separate from the main application server, and the reconciliation engine automates 2-way and 3-way matching with backdated support, staggered scheduling, and customizable audit-ready outputs. The Control Center dashboard provides visual workflow builders for routing rules, payment analytics, and operations management. Cost observability tools drill into scheme, interchange, and acquirer fees to detect anomalies and optimize processing costs. The modular architecture allows deploying individual components — routing, retries, vaulting, observability, or the full suite — without vendor lock-in. The web client SDK collects payment information with prebuilt UI components and supports WooCommerce integration. Deploy via Docker Compose with the app server, control center, card vault, and PostgreSQL. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

GCHQ open-sourced its "Cyber Swiss Army Knife", and CyberChef became the web app security analysts, incident responders, and CTF players reach for when data needs decoding, decrypting, or dissecting. Its interface is four panes: paste or drag input (files up to 2GB), search a categorized library of hundreds of operations, drag them into a recipe with arguments, and read the output. Operations span Base64, hex, and XOR encoding; AES, DES, and Blowfish encryption; classical ciphers from Caesar to Railfence; hashes and checksums; compression; regex and string extraction of IPs, domains, and URLs; timestamp conversion; and parsers for IPv6, X.509 certificates, and more. Recipes chain arbitrarily - convert from a hexdump then decompress, decrypt AES pulling the IV from the cipher stream, or let the Magic operation auto-detect several layers of nested encoding. Auto Bake re-runs the recipe live as input or arguments change, Step executes one operation at a time for debugging, and flow control (forks, subsections, registers) applies different operations to different parts of the data. Recipes save to files or share as URLs encoding the full pipeline. Crucially, CyberChef is entirely client-side JavaScript - nothing uploads anywhere - and self-hosting guarantees an unmodified copy inside your own network, where malware artifacts belong.

The utilities engineers otherwise scatter across a dozen ad-laden websites - 80+ of them - live together in IT-Tools, one fast, polished web app. Crypto covers JWT decoding, MD5 through SHA-512 hashing, HMAC and bcrypt generation, RSA key pairs, and password strength analysis. Converters handle JSON to CSV, YAML, and TOML, Base64 files, URL encoding, HTML entities, color formats, and Docker run commands to Compose files. Generators produce UUIDv4, ULID, BIP39 mnemonics, QR codes (including Wi-Fi QR), and tokens; text tools include a regex tester, diff viewer, slug and case converters; web utilities parse URLs and user agents, look up HTTP status codes and MIME types, and inspect Open Graph metadata; plus a cron parser, chmod calculator, and more. The privacy argument is the point: JWTs contain user IDs, hashes derive from passwords, JSON dumps hold PII - exactly the inputs you least want a third-party utility site to log. IT-Tools is a frontend-only static bundle (Vue/TypeScript, GPL-3.0, 39k+ GitHub stars) served by Nginx in one container, so everything runs client-side on your infrastructure with nothing transmitted anywhere. New tools ship roughly monthly, and a scaffolding script makes adding custom ones straightforward.

With over 4,300 GitHub stars and a v3 release adding built-in user management, team views, and multi-language support, Kubero has established itself as the most feature-complete open-source Heroku alternative running natively on Kubernetes. The platform operates as a Kubernetes operator with two containers — kubero-ui and the operator — storing all state in etcd without an external database. Developers push code via Git integration with GitHub, GitLab, Bitea, or Gitea, and Kubero automatically builds using Buildpacks, Nixpacks, Runpacks, or Dockerfiles, then deploys to the configured domain with SSL via cert-manager. CI/CD pipelines support up to four staging environments — review, test, staging, and production — with per-stage environment variable isolation and ephemeral review apps that spin up on pull request open and tear down on close. The template catalog includes over 170 pre-configured applications like WordPress, Grafana, and PostgreSQL deployable in one click, while managed add-ons provide highly available PostgreSQL, Redis, MySQL, Kafka, CouchDB, Elasticsearch, and MongoDB alongside your applications. Security features include Trivy vulnerability scanning, GitHub and OAuth2 single sign-on, basic auth, and a role-based permission system with API tokens. The NestJS backend with Vue.js and Vuetify frontend provides application metrics, real-time logs, a built-in web console for container access, scheduled cronjob management, and deployment notifications via Discord, Slack, or webhooks. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.