DeepSeek Harness gained over 60,000 GitHub stars within hours of its August 2026 launch, establishing itself as the first fully modular open-source agent runtime where literally every component is a swappable plugin. Built on the Cordis framework—a programming paradigm for spatiotemporal composability—dsh decomposes the entire agent stack into independently replaceable pieces: model adapters for DeepSeek, Anthropic, OpenAI, AWS Bedrock, Azure, and Google Gemini; tool registries covering bash execution, file system operations, web search, subagent delegation, and todo management; plus session stores, sandboxes, approval policies, orchestration loops, and the user interface itself. Four operating modes serve different workflows: Standard provides the full toolset, Code mode uses model-generated code to compose multi-round tool calls, Minimal strips down to a shell and editor for benchmarking, and Creator mode lets developers inspect the running runtime and test Cordis plugins in memory. The kernel handles plugin mounting, unmounting, and dependency resolution while typed events and services coordinate between components. Profiles and bundles allow the same codebase to produce entirely different products—a terminal coding agent, a browser-based workspace, a headless automation service, or an ACP/JSON-RPC endpoint—by swapping YAML configuration layers. Session history is stored as an append-only event stream for full trajectory replay, and project-level hooks on agent lifecycle events enable fine-grained behavioral customization. MCP client integration connects to external tool servers, while Agent Client Protocol enables programmatic orchestration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

NanoClaw delivers a radically simple alternative to OpenClaw — a single Node.js process and a handful of files that provide the same core functionality with true container-level security isolation. Agents execute inside Docker containers on Linux or Apple Containers on macOS, where even root access inside the sandbox cannot reach the host filesystem. The platform natively runs Claude Code via Anthropic's official Claude Agent SDK, with drop-in alternatives including OpenAI Codex, OpenRouter via OpenCode, Google, DeepSeek, and local open-weight models via Ollama — configurable per agent group. Multi-channel messaging connects WhatsApp, Telegram, Discord, Slack, Microsoft Teams, iMessage, Matrix, Google Chat, Webex, Linear, GitHub, WeChat, and email via Resend, installed on demand through skill commands. Each agent group receives its own CLAUDE.md memory file, isolated filesystem, container sandbox, and session state — a prompt injection in one group cannot exfiltrate data from another. The OneCLI Agent Vault handles credentials so agents never hold raw API keys, while approval-gated self-modification allows agents to request new packages or MCP servers that administrators must authorize. Scheduled tasks run recurring jobs inside containers with message delivery back to users. The setup script handles dependencies, authentication, and container configuration through Claude Code conversation. Deploy on any Docker-capable Linux server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Buzz delivers the first production workspace where humans and AI agents operate as cryptographically equal team members on a self-hosted Nostr relay. The Rust-based backend stores every message, code patch, CI result, review comment, and workflow step as a signed Nostr event in a unified PostgreSQL-backed event log with Redis pub/sub for real-time presence and S3/MinIO for media storage. The integrated Git forge implements NIP-34, turning feature branches into dedicated channels where patches, reviews, and merge decisions live alongside the discussion that produced them — eliminating the split between chat tools and code hosts. Through the open Agent Client Protocol, Buzz natively supports Goose, Anthropic Claude Code, and OpenAI Codex as first-class channel members with scoped permissions, their own audit trails, and the ability to create patches, run workflows, and orchestrate multi-step automations via YAML-defined triggers including message events, reactions, schedules, and webhooks. The Tauri-based desktop client runs on macOS, Windows, and Linux, while buzz-cli provides agent-first JSON I/O for headless automation. Deploy via Docker Compose with the production bundle in deploy/compose/, Railway one-click, or build from source requiring Rust 1.88+, Node 24+, and pnpm. Multi-community mode scopes tenant data by domain with NIP-42 Schnorr authentication, rate limiting, and hash-chain audit logging. 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 83,000+ GitHub stars and $18.8M in Series A funding, OpenHands delivers the leading open-source platform for AI coding agents that scored 68.4% on SWE-bench Verified with Claude Opus 4.6, outperforming Devin 2.0's publicly reported 45.8%. The Agent Canvas web UI organizes work into persistent conversations where agents edit files, run shell commands, browse the web, and execute multi-step development tasks inside isolated Docker sandbox containers. The observe-plan-act loop drives agent behavior: the Python controller manages LLM abstraction via LiteLLM routing to 100+ providers including OpenAI, Anthropic, Google, DeepSeek, Qwen, Llama, and local Ollama models. Built-in skills for code review, Docker management, PRD generation, repo-rules enforcement, release notes, and test running attach to conversations automatically via auto-discovery or trigger-based activation. The Automations system schedules recurring agent tasks with configurable templates for CI workflows, dependency updates, and documentation generation. MCP server integration enables agents to access external tools and data sources. The REST API powers an OpenAI-compatible endpoint for connecting agents to chat UIs, IDEs, and voice platforms. GitHub, GitLab, Slack, and Jira integrations enable pull request reviews, issue resolution, and team notifications. The SDK provides Python and REST APIs for embedding agents in custom tools with local or cloud execution, custom agent behaviors, and Kubernetes deployment. On RepoCloud, deploy OpenHands on a dedicated VPS with Docker socket access, persistent project storage, root SSH access, and complete control over your AI development infrastructure, all under the MIT license.

Langflow turns LLM application development into a visual canvas where every node maps to a real LangChain primitive (chains, agents, retrievers, memory, vector stores, and tools) that teams wire together without writing integration boilerplate. The platform supports 15+ LLM provider components including OpenAI, Anthropic, Google Gemini, Mistral, Groq, Cohere, Azure OpenAI, HuggingFace, and Ollama for fully local inference, with LiteLLM proxying to over 100 additional providers through a single OpenAI-compatible endpoint. Vector database integrations cover Pinecone, Weaviate, Chroma, Qdrant, Astra DB, OpenSearch, FAISS, and Milvus, while built-in Knowledge Bases introduced in version 1.8 allow RAG pipelines without any external vector service. Multi-agent orchestration enables agent-to-agent communication with conversation management, persistent Memory Bases for cross-session context retrieval, and step-by-step reasoning visibility in the interactive Playground. Every flow automatically becomes a callable REST API endpoint via the /run route and an MCP server exposable to Claude Desktop, Cursor, or any MCP-compatible client. Every component is a real Python class that developers can customize, extend, or replace, while Extension Bundles package third-party integrations as independent pip packages for modular installation. Tool integrations include web search, Slack, Gmail, Google Drive, GitHub, and custom REST API calls. Docker deployment with PostgreSQL persistence runs on port 7860. Backed by 153,000+ stars and DataStax. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

QM is Y Combinator's internal multiplayer agent infrastructure that shifts AI agents from personal assistants to shared company operating layer. The headless TypeScript core runs on Node.js with Fastify handling HTTP, Slack integration via Bolt, and a web UI built with Vite and Lit. PostgreSQL stores sessions, memory, queue state, and audit logs. Every person and every Slack channel gets an isolated sandbox with its own durable file system, installed tools that persist across runs, private memory, keychain view, permissions, and background crons. The harness-agnostic architecture routes agent tasks through Pi, OpenCode, Codex, or Claude Code without vendor lock-in, with production implementations swapping via a single wiring file. Three org-level security postures gate execution: Strict requires human approval for every tool call, Auto applies automated content screening, and Dangerous removes all pauses. Skills are scope-owned and shareable by grant, with admin-gated promotion to the entire organization and skill packs importable from Git repositories. The web apps feature lets agents spin up custom internal applications published to specific users. The qm CLI bootstraps operator-owned deployment directories with digest-pinned release images, infrastructure rendering, secret management, and live verification checks for Docker, Fly.io, or AWS ECS Fargate targets. On RepoCloud, deploy QM on a dedicated VPS with PostgreSQL persistence, Docker socket access, root SSH access, and complete control over your multiplayer agent infrastructure, all under the MIT license.

Relaticle delivers the first CRM built from the ground up for both human operators and AI agents — a self-hosted platform where Claude, GPT, Gemini, or any custom model connects through a production-grade MCP server exposing 30 tools for full CRUD operations across companies, people, opportunities, tasks, and notes without a single line of integration code. The 22 custom field types include text, email, phone, currency, date, select, multiselect, entity relationships, conditional visibility rules, and per-field encryption — all configurable through the UI without database migrations or code changes. Multi-team isolation enforces data boundaries through a 5-layer authorization system with team-scoped workspaces, API tokens, and granular permissions. The JSON:API REST surface provides Spatie QueryBuilder filtering, sorting, and pagination with schema discovery endpoints that let agents introspect your data model at runtime. A built-in AI chat connects directly to CRM data for natural language queries, while the external MCP server gives any compatible agent the same 30-tool access. Docker Compose deployment runs five containers — app (nginx + PHP-FPM), Horizon queue worker, scheduler, PostgreSQL 17, and Redis 7 — with automatic migrations on startup and demo data seeding for new teams. 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.

Open-source alternative to OpenAI's Canvas — a collaborative writing and coding environment where AI agents help you draft, edit, and refine documents through an agentic architecture built on LangGraph. The dual-mode editor combines a BlockNote rich text editor for live-rendered markdown with a CodeMirror-based code editor supporting syntax highlighting across multiple programming languages, letting you switch between prose and code artifacts within the same session. The built-in reflection agent automatically generates style rules and user insights from your chat history, storing them in a shared LangGraph memory store that persists across sessions for increasingly personalized assistance. Pre-built quick actions provide one-click access to common writing transformations including summarize, expand, simplify, and translate, while coding actions offer explain, refactor, add comments, and convert between languages. The monorepo architecture separates the Next.js 14 frontend from the LangGraph agent backend, connecting via HTTP and WebSocket protocols through the @langchain/langgraph-sdk client. Seven LLM providers are supported out of the box — OpenAI, Anthropic Claude, Google Gemini, Fireworks AI, Groq, Azure OpenAI, and local Ollama models — with Supabase handling authentication and data persistence. Deploy via Docker or build from source. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Trusted by Mistral AI, PayPal, Groq, and Synthesia with over 10,300 GitHub stars and Y Combinator backing, Lago is the open-source billing engine that handles usage-based, subscription-based, and hybrid pricing models through a single API-first platform — replacing the need to build custom billing logic or depend on opaque SaaS pricing infrastructure. Real-time event ingestion via ClickHouse processes billable events with deduplication and multiple aggregation methods including count, sum, unique count, max, and weighted sum, while graduated pricing tiers, package-based billing, and percentage-based fees model any pricing strategy from simple subscriptions to complex marketplace commission structures. Automated invoice generation calculates charges according to configurable billing cycles with grace periods, proration for mid-cycle changes, and credit note issuance for refunds and adjustments. Prepaid credits enable pay-in-advance models where customers purchase credit blocks and draw down as usage accumulates, while entitlements tie feature access directly to billing plans for automated provisioning and de-provisioning. Payment orchestration integrates natively with Stripe, Adyen, and GoCardless with automatic retry logic, dunning workflows for failed payments, and multi-gateway routing. Revenue analytics provide cross-stream visibility into MRR, usage trends, churn, and revenue drivers through dedicated API endpoints. The customer portal embeds into your application for self-service invoice access and usage monitoring. 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 nearly 12,000 GitHub stars and a lineage tracing back to Sphinx Search, Manticore Search is the C++ search database that delivers the full-text, vector, and hybrid search capabilities of Elasticsearch at a fraction of the resource cost — starting in under a second and consuming just 40MB RAM for an empty instance. The SQL-first interface speaks the MySQL wire protocol, meaning mysql client, MySQL Workbench, and any MySQL-compatible driver connects natively without adapters, while the HTTP JSON API provides RESTful access for modern applications. Over 20 full-text operators handle proximity search, quorum matching, field-start and field-end constraints, MAYBE operators, and regex patterns, backed by stemming, lemmatization, stopwords, synonyms, wordforms, and advanced morphology in 70+ languages. Vector search with HNSW indexing enables semantic similarity queries, and hybrid mode combines keyword relevance with vector distance in a single ranked result set using a cost-based query optimizer. Real-time indexing delivers sub-second document availability after insert, sharded tables distribute data across nodes, and Galera-based synchronous replication ensures high availability. Conversational search via CREATE CHAT MODEL and CALL CHAT integrates LLM-backed responses with KNN retrieval and conversation history directly inside the database. Client libraries ship for PHP, Python, JavaScript, TypeScript, Java, Go, Rust, and Elixir. Columnar storage via the Manticore Columnar Library handles analytical workloads on large datasets. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPLv3 licensed.

With over 6,500 GitHub stars, HolaOS bills itself as an "open agent computer" that reimagines the traditional operating system as a shared workspace where humans and AI agents collaborate across files, browsers, and 100+ integrated tools simultaneously. Unlike chat-only interfaces, HolaOS places live application UIs—Notion-style editors, browsers, custom workspace apps—side by side with the agent conversation, so operators always see what agents are doing and can intervene at any moment. The persistent memory system stores workspace knowledge locally as Markdown files and embedded vectors via SQLite vec, enabling RAG-powered recall that survives session boundaries without the typical context window bloat. Safe Session Compaction reserves roughly 70% of the model context window for fresh reasoning while folding older history into structured checkpoints that retain goals, constraints, progress, and decisions. Agents connect to Linear, GitHub, Slack, Jira, HubSpot, Gmail, and dozens more through one-click OAuth, automatically fetching relevant signals and converting scattered app data into working memory. BYOK support for Claude, GPT, and Gemini models lets operators use their own API keys at zero markup, while built-in Kimi K3 and GLM-5.2 models provide ready-to-use alternatives. Skills package reusable workflows that any agent can invoke on demand, and scheduled triggers enable autonomous digests, monitors, and reports. The runtime supports independent server deployment alongside the desktop client. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Modified Apache 2.0 licensed.

OpenFGA answers the question 'can this user perform this action on this resource?' in single-digit milliseconds, implementing Google's Zanzibar paper as a production-ready authorization engine adopted by Auth0, Grafana Labs, Canonical, Docker, Agicap, and Read.AI. The server exposes both gRPC and HTTP APIs for authorization queries including Check, ListObjects, ListUsers, Expand, and the high-throughput BatchCheck endpoint that deduplicates and processes multiple authorization decisions in a single request. Authorization models combine relationship-based access control with role-based and attribute-based patterns through a purpose-built DSL that supports contextual tuples, conditional relationship tuples with CEL expressions, and time-based filtering via the ReadChanges API. Storage backends include PostgreSQL 14+, MySQL 8, and SQLite in beta, with an in-memory adapter for development and testing. Official SDKs for Java, .NET, Node.js, Go, and Python provide type-safe client integration, while a Terraform provider enables infrastructure-as-code management of authorization stores and models. The built-in browser playground at port 3000 lets developers visually model authorization schemas, write relationship tuples, and test access control queries interactively before deployment. OpenTelemetry instrumentation integrates with existing monitoring infrastructure, and Helm charts simplify Kubernetes deployment. A VS Code extension provides syntax highlighting and validation for FGA model files, and GitHub Actions automate model testing in CI/CD pipelines. A CNCF incubating project with transparent governance. 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.

Originated as Alibaba Group's official internal AI code review assistant serving tens of thousands of developers and identifying millions of code defects over two years before open-sourcing in May 2026 — now at 21,000+ GitHub stars — Open Code Review is the production-hardened platform that proves enterprise-grade code review can be fully open-source under Apache 2.0. The hybrid architecture separates deterministic engineering pipelines (file selection, diff parsing, rule matching for NPE, thread-safety, XSS, and SQL injection across 10+ languages) from LLM-powered agent reasoning with tool-use capabilities including FileRead, CodeSearch, and cross-file context inspection, consuming approximately one-ninth the tokens of general-purpose coding agents while delivering line-level precise comments with severity and confidence scoring. The bundled web dashboard (port 4173) provides review management, findings triage, result browsing, and direct GitHub posting without external dependencies, while the session viewer (port 5483) renders full LLM request/response traces for debugging and auditing. Integration spans GitHub Actions, GitLab CI, GitFlic CI, and Gerrit with delegation mode enabling Claude Code, Cursor, and other AI agents to leverage OCR's engineering logic alongside their own LLM reasoning. Supports OpenAI, Anthropic, Google Gemini, DeepSeek via built-in providers plus Ollama and vLLM for air-gapped deployments. 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 over 27,000 GitHub stars and an ecosystem of 1,900+ plugins covering every major cloud provider, database, and SaaS platform, Kestra is the orchestration engine that brings Infrastructure as Code principles to workflow automation — defining complex multi-step pipelines in readable YAML that execute across any language, runtime, or infrastructure boundary. The built-in VS Code-style editor provides syntax highlighting, auto-completion, real-time validation, and an AI Copilot that generates workflow YAML from natural language descriptions. Tasks execute in Python, Node.js, Go, R, Shell, SQL, or any Docker container, with event-driven triggers listening for file arrivals on SFTP and cloud storage, messages from Kafka, Redis, Pulsar, AMQP, MQTT, NATS, AWS SQS, Google Pub/Sub, and Azure Event Hubs in real time. The topology view visualizes workflow DAGs with execution state, duration, and output artifacts for each task node. Namespaces organize workflows into isolated environments with configurable secrets, while subflows enable modular composition with inputs, outputs, and conditional branching. Retry policies, timeouts, error handlers, and automatic backfills for missed schedules ensure reliability across production workloads. Git integration pushes workflows directly to branches from the UI with CI/CD pipeline support for automated deployment. The REST API enables programmatic workflow management, execution triggering, and resource provisioning. 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.

SpiderFoot is an open-source OSINT automation platform, replacing hours of manual reconnaissance with automated intelligence gathering across more than 200 data collection modules. The platform accepts ten distinct target types including IP addresses, domains, hostnames, network subnets, ASNs, email addresses, phone numbers, usernames, person names, and Bitcoin addresses, then feeds them through a publisher-subscriber event bus where each module's findings trigger downstream analysis automatically. SpiderFoot queries Shodan, VirusTotal, HaveIBeenPwned, AlienVault OTX, Censys, crt.sh, WHOIS databases, social media platforms, breach databases, and dozens more sources, with most modules requiring no API keys and many offering free tiers for those that do. The YAML-configurable correlation engine applies 37 pre-defined rules to identify relationships between discovered data points, flagging patterns like shared infrastructure, credential exposure, and domain reputation anomalies. Results export in CSV, JSON, and GEXF graph formats for integration with external analysis tools. TOR integration enables dark web searching, and SpiderFoot can invoke external tools including DNSTwist, Whatweb, Nmap, and CMSeeK for deeper technical assessment. The embedded web server delivers an intuitive dashboard for scan management, data visualization, and result exploration alongside a full command-line interface for scripted automation. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 24,000 GitHub stars and origins in the MemGPT research paper on virtual context management, Letta has evolved into the leading open-source platform for building AI agents that maintain persistent memory, identity, and continuity across sessions rather than operating as stateless prompt-response loops. The core architecture uses memory blocks — structured, labeled text chunks that reside permanently in the agent's context window — allowing agents to programmatically rewrite their own memory, learn new skills, and improve through a sleeptime dreaming process that runs reflection and memory organization during idle periods. The self-hosted App Server deploys via Docker and exposes a WebSocket API on port 4500, letting the TypeScript Agent SDK connect from any application using local, remote, or cloud backends. Agents support git-versioned memory through MemFS where every memory change is tracked and auditable, multi-agent communication via subagents, scheduled tasks, and integration with messaging platforms including Slack, Discord, Telegram, WhatsApp, and Signal. The platform is fully model-agnostic, routing to OpenAI, Anthropic, xAI, or self-hosted open-weight models through Ollama depending on cost, performance, and data residency requirements. The Agent File format serializes complete agent state — memory, skills, prompts, and conversation history — into portable snapshots. Desktop applications for macOS, Windows, and Linux provide native interfaces alongside the terminal CLI and web chat at chat.letta.com. 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.

Your dashboards deserve version control, code review, and reproducible builds, just like the rest of your stack. DAC lets you define interactive data dashboards in YAML or TSX, validate them in CI, and serve them from a single Go binary that embeds a full React frontend. Choose from 21 chart types including line, bar, area, pie, scatter, bubble, funnel, sankey, heatmap, calendar, sparkline, waterfall, gauge, treemap, radar, and candlestick, plus metric cards, data tables, text blocks, and image widgets. The built-in semantic layer lets you define metrics and dimensions once in reusable model files, then reference them from any widget while DAC generates the SQL automatically. Connect to Postgres, MySQL, Snowflake, BigQuery, Redshift, Databricks, and DuckDB through standard Bruin connection configs. Interactive filters with date pickers, dropdowns, multiselects, and search inputs inject values via Jinja templating and re-execute only affected widgets. Live reload via Server-Sent Events refreshes connected browsers instantly when you save a file. Export dashboards as self-contained static HTML with baked-in query results for S3, GitHub Pages, or offline sharing, and render slide decks via the Google Slides export command. On RepoCloud, deploy DAC on a dedicated VPS with root SSH access and persistent storage for your dashboard definitions and database connections under the AGPL-3.0 license.

No cookies, no fingerprinting, no cross-site tracking, no personal data collection - Umami's privacy contract is the foundation of the open-source web analytics platform. IP addresses are hashed rather than stored, which makes it GDPR, CCPA, and PECR compliant by default - the consent banner can come off the site entirely. The tracking script is under 2 KB, roughly 20x smaller than Google Analytics, so measurement stops being a page-weight tax. The dashboard covers the core metrics - pageviews, visitors, bounce rate, visit duration, referrers, browsers, devices, and countries - with any date range and filtering by country or device. Beyond pageviews, custom events track clicks, form submissions, and signups via a data attribute or one JavaScript call, and advanced reports add funnels, user journeys, retention and cohort analysis, goals, and automatic UTM campaign tracking. Anonymous session views show individual visitor activity without identifying anyone. Teams share websites with role-based access, one instance manages unlimited sites, and a full REST API exposes every metric programmatically. MIT-licensed and self-hosted on PostgreSQL or MySQL via Docker, your analytics data never leaves your infrastructure.