DeerFlow 2.0 is ByteDance's ground-up rewrite that transforms what began as a Deep Research framework into a batteries-included super agent harness handling tasks lasting minutes to hours autonomously. Built on LangGraph and LangChain, the runtime orchestrates a lead agent that plans, decomposes, and delegates to sub-agents executing in isolated Docker or Kubernetes sandboxes with persistent filesystem access, while an extensible skills system lets developers add capabilities as Python functions or MCP servers with OAuth token flows. The harness ships with long-term memory using persistent event loops with per-agent isolation, scheduled task execution via cron, context engineering with manual compaction, and a web UI at localhost:2026 for interactive sessions. Model support spans OpenAI GPT-4o/GPT-5, Anthropic Claude via OAuth, Google Gemini, DeepSeek, Qwen via vLLM, and OpenRouter-compatible gateways with per-model pricing configuration. IM channel integration connects Telegram, Slack, Feishu/Lark, Discord, WeChat, WeCom, DingTalk, and Buzz without requiring a public IP — all using long-polling or WebSocket transports. Production deployment uses Docker Compose with nginx reverse proxy, PostgreSQL or SQLite persistence, Redis stream bridges for multi-worker scaling, and lease-based run ownership with automatic orphan recovery. The terminal workbench TUI enables headless operation. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Open-sourced by the Databricks AI team under Apache 2.0 and reaching over 8,500 GitHub stars within two months of launch, Omnigent introduces the meta-harness concept: a common orchestration layer that sits above existing AI coding agents and makes them interoperable parts of a governed, collaborative system. The platform wraps Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, and any custom agent defined in a simple YAML configuration file into sandboxed sessions with a uniform API, then exposes each session through the terminal, a web UI, a native desktop application, mobile interfaces, and a REST API. Built-in multi-agent workflows include Polly, a coding orchestrator that delegates tasks to parallel sub-agents in separate git worktrees and routes each diff to a reviewer from a different vendor, and Deep Research, which plans sub-queries, searches the live web through MCP servers, reads full pages, and cross-checks claims across independent sources. Contextual security policies go beyond static allow/deny rules by maintaining per-session state to enforce spend caps, model routing, approval gates for destructive actions, PII blocking, and repository-scoped write restrictions across server-wide, per-agent, and per-session levels. The OS sandbox restricts filesystem and network access while intercepting egress requests to inject credentials only on approved calls. Cloud sandbox providers including Modal, Daytona, E2B, CoreWeave, Kubernetes, and Databricks launch disposable execution environments per session. 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.

MateClaw delivers a multi-agent AI platform where digital employees run as persistent team members with roles, goals, and accumulated skills rather than stateless chat completions. The Spring Boot backend on Spring AI Alibaba provides ReAct iterative reasoning and Plan-and-Execute decomposition on a StateGraph runtime, with parallel delegation between employees and dynamic context pruning for multi-step tasks. Five career templates ship ready (Product Researcher, Customer Support, Knowledge Curator, Data Analyst, Executive Assistant) while custom employees inherit configurable backstories, pixel-art avatars, and dedicated tool bindings. The MCP integration supports stdio, SSE, and Streamable HTTP transports with per-employee tool isolation preventing capability bleed between agents. ACP bridges bring Claude Code, Codex, and other coding agents in as first-class employees. Workflow orchestration composes multiple employees and system actions into publishable linear DSL processes with seven step modes: sequential, fan_out, collect, conditional, await_approval, dispatch_channel, and write_memory. The trigger system wires cron schedules, webhooks, channel messages, employee lifecycle events, content matches, and workflow completions to automated flows. The Admin Runtime Console provides real-time visibility into running employees with token usage tracking and one-click force-recycle. Spring Boot Actuator monitoring, full audit trail, and per-channel error isolation deliver production-grade reliability. 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.

Accepted as a NeurIPS 2025 Spotlight paper and rapidly approaching 6,000 GitHub stars, AI-Researcher from the Hong Kong University Data Science Lab delivers the first fully autonomous scientific research system — a multi-agent platform that takes a list of reference papers and returns a complete research contribution with working code, validated experiments, and a formatted academic manuscript. The pipeline orchestrates five distinct phases: a Resource Collector systematically gathers materials from arXiv, IEEE Xplore, ACM Digital Library, Google Scholar, GitHub, and Hugging Face; an Idea Generator performs gap analysis against semantic embeddings to produce 3-5 novel hypotheses with feasibility scores; an Algorithm Designer transforms concepts into functional implementations; a Validation Engine automates testing, performance evaluation, and iterative optimization; and a Manuscript Creator generates polished full-length papers with figures, tables, and citations. The Gradio-based web GUI provides intuitive tabs for environment configuration, example selection, and real-time monitoring of research progress, while the production deployment at novix.science offers immediate browser access without local setup. Scientist-Bench provides a standardized benchmark comprising state-of-the-art papers across diverse AI research domains for evaluating autonomous research capabilities. The system supports multiple LLM providers including OpenAI, Anthropic, Google Gemini, and OpenRouter models with per-task routing for cost optimization. Deploy via Python with pip dependencies or Docker containerization. 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.