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.

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.

With over 14,000 GitHub stars and 41 releases since its May 2026 launch, Prime Agent delivers a fundamentally different approach to AI coding agents by treating the agent's own operating environment as programmable state that improves through use. The Recursive Language Model architecture provides the model exactly one tool — a persistent IPython kernel — where file operations, shell commands, subagent delegation via rlm() function calls, and context management all happen through code rather than rigid tool-calling schemas. Subagents launch as independent sessions with their own model, kernel, and history, communicating results through agent_message.send() without blocking the parent. The Continual Harness stores supplemental prompts, memories, skill descriptions, and reusable subagent specifications as durable state that the /refine command updates through small, evidence-backed edits with full rollback by ID. Daemon-backed sessions keep running when the terminal disconnects, with automatic context compaction summarizing older messages while preserving recent state. The TUI provides an Agent View for monitoring, switching between, and steering multiple live sessions simultaneously. Autonomous mode operates within configurable turn, token, and time budgets with user-defined quality gates. Persistent goals, heartbeats, and scheduled prompts maintain continuity across terminal sessions. Compatible with Anthropic Claude, OpenAI, Google Gemini, local models via Ollama or vLLM, and Prime Inference endpoints. Install via a single curl command on Linux or macOS. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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.

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.

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 33,000 GitHub stars and a codebase written in 92.9% Rust for maximum performance and memory safety, Tabby is the most widely adopted self-hosted alternative to GitHub Copilot — delivering real-time code completions entirely on your own infrastructure with zero code leaving your network. Deploy a single Docker container on any NVIDIA CUDA, Apple Silicon Metal, AMD ROCm, or CPU-only server and connect VS Code, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, GoLand), Vim, Neovim, and Emacs through native extensions. The completion engine supports a curated registry of models including StarCoder2 (1B to 15B parameters), DeepSeek-Coder, CodeLlama, CodeGemma, Qwen2.5-Coder, and Mistral Code — swappable at runtime through the admin dashboard without redeployment. Repository indexing parses your Git repositories and feeds project-specific types, function signatures, and patterns into completion context via RAG, producing suggestions that understand your codebase rather than generic boilerplate. The Answer Engine provides instant responses to code queries within the IDE, while inline chat enables contextual code editing and explanation without switching windows. The admin dashboard manages per-developer API tokens, usage analytics, and model configuration. Enterprise features include SSO via LDAP, OAuth, and SAML, role-based access control, and audit logging for compliance environments. A single RTX 4090 workstation serves a team of 10-15 developers with sub-500ms completion latency. 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.

Pi Web is a browser interface for the Pi coding agent ecosystem, providing a visual workspace that reads the same local configuration and session files as the CLI. The session workspace groups conversations by project with running state indicators, context usage percentages, cost tracking, and compaction details, while two branching modes let users create independent session files from earlier messages or fork branches within existing sessions to explore alternative coding directions. Real-time streaming via Server-Sent Events delivers agent responses with structured Markdown rendering, thinking steps, tool call visualization, and image drag-and-drop input. The project file explorer browses working directories with syntax-highlighted source preview, Git diff inspection, and rendering for Markdown, images, audio, PDFs, and DOCX files with automatic refresh. Git worktree support switches checkouts from the sidebar while keeping sessions from the same repository grouped together. The Models panel manages provider authentication via OAuth and API keys, model selection, model smoke tests, and models.json configuration shared bidirectionally with the CLI agent. The Skills panel lists, searches, installs, and toggles agent skills without terminal access. The interface ships with English and Simplified Chinese translations, light and dark themes, a chat minimap, keyboard shortcuts, and completion sounds. Basic Auth protects remote access when binding to non-loopback addresses. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

The fastest tool on the public Martian Code Review Bench at 77 seconds per PR with competitive F1 scores — while every higher-scoring competitor takes 5 to 14 times longer — Mira is the fully open-source AI code reviewer that ships the entire feature surface other tools gate behind per-seat subscriptions: indexed PR reviews with full-repo context, streaming walkthroughs posted within seconds, inline vulnerability scanning from hourly OSV.dev polls, org-wide package inventory answering "which repos use [email protected]?" in one query, interactive dependency graphs with blast-radius SVG rendering via ReactFlow, a learning loop that synthesizes rules from rejected comments and human review patterns on merged PRs, and cost telemetry showing actual spend per repo and per model. Unlike CodeRabbit, Greptile, and GitHub Copilot code review which are SaaS-only with per-seat pricing, Mira runs as a single Docker image on your infrastructure with your LLM key through OpenRouter (fronting Anthropic, OpenAI, Google Gemini, DeepSeek) or direct to Ollama and vLLM for fully air-gapped deployments. The engine indexes Python, TypeScript, Go, Rust, Java, C/C++, C#, Swift, Kotlin, Scala, and PHP with per-file symbol extraction, enabling multi-file reasoning across diffs rather than isolated line-by-line review. Integrates with GitHub, GitLab, and Forgejo via webhook with full feature parity. 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 15,500 GitHub stars and over 1,100 forks, Plandex delivers a terminal-based AI coding agent purpose-built for the complex, multi-file tasks that overwhelm single-file AI assistants. The Go-powered server maintains a cumulative diff review sandbox that quarantines all AI-generated changes from your project files until you explicitly approve them — enabling 20-file refactors where you cherry-pick good changes and reject bad ones without touching git. A 2M token effective context window loads only what each step requires, while tree-sitter project maps index repositories exceeding 20M tokens across 30+ programming languages, providing structural awareness of class hierarchies, function signatures, and import graphs without burning tokens on full file content. The configurable model pack system assigns different models to different roles — Claude for planning, GPT for coding, Gemini for summarization — supporting Anthropic, OpenAI, Google, OpenRouter, Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, and Ollama for local models. Full auto mode handles end-to-end autonomous workflows including high-level planning, context loading, implementation, terminal command execution, and automated debugging of both terminal and browser applications. The interactive REPL provides fuzzy auto-complete, version-controlled sandbox branching, rewind to any previous point, and Git integration for commit message generation. The Plandex Server exposes 60+ REST API endpoints for programmatic orchestration across organizations, projects, plans, and branches. Deploy via Docker Compose for self-hosted operation with your own API keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.