#Multi-agent (13)

ByteDance's open-source super agent harness (82k+ stars). 2.0 is a ground-up rewrite sharing no code with 1.x: sub-agents, extensible skills, sandbox and file system, long-term memory, session goals, plus Manual Context Compaction that hands context management back to the operator. Positioning lifted from a deep-research framework to a runtime for any task. Not benchmarked by us; graded needs-reproduction.

Agent HarnessMulti-agentSkill System

Python83k11k346

paperclipai/paperclipMIT

Paperclip: run a company with a team of AI agents

Open-source orchestration for teams of AI agents: a Node.js server and React UI where you bring your own agents, set goals, and track work and spend from one dashboard. It looks like a task manager; underneath sit org charts, budgets, governance, goal alignment and agent coordination. It manages business goals, not pull requests. MIT, self-hostable.

Agent orchestrationMulti-agentGovernance

TypeScript81k15k395

multica-ai/multicaNOASSERTION

Multica: AI coding agents that show up on the board

An open-source, self-hostable workspace where you assign issues to AI coding agents the way you would to a teammate: they pick up the work, run on a runtime you control, comment as they go, and hand results back for review. Works with 26 agent CLIs and keeps intent, runs, decisions and diffs on one issue, with code never leaving your machine.

Agent orchestrationCoding AgentMulti-agent

Go51k6.6k184

huangruiteng/loopxApache-2.0

LoopX: An Open, Stateful Control Plane for Long-Horizon Agents

LoopX is an open, provider-neutral, stateful control plane that runs on top of Codex, Claude Code, Cursor and other agent harnesses instead of replacing them. It preserves objectives, gates, todos, scope, evidence, quota and handoffs as durable state across turns, restarts and agents, and uses quota to decide whether a loop may continue, keeping multi-day work reviewable, restartable and handoff-able.

Agent infrastructureControl planeLong-horizon agents

Python5.7k50427

AI CodingDevelopmentTopC

Qoder: Alibaba agentic platform for real work - nine product lines on one knowledge engine

Qoder is the agentic coding platform from Alibaba, positioned officially as an agentic platform for real work: not an editor but an end-to-end loop - understand the task and context, plan, call tools, verify results, iterate toward the deliverable - resting on three stated principles (context engineering, agent autonomy, goal-directed loops), with nine product lines sharing one knowledge engine (desktop Qoder and Qoder IDE coexisting rather than replacing each other, Editor and Quest forms, a JetBrains plugin, Qoder CLI, cloud agents and more); session history and memory are stored separately but can be imported from the IDE. Repo Wiki is generated locally by multiple agents, never uploads the codebase, is off by default and supports Auto Update, Auto Export and Citation back to source locations. Quest has four drives - Agent, Experts, Goal and Spec (convertible to scheduled tasks): Spec runs requirement clarification (multiple choice, with Recommend / Continue / Skip), a structured Spec covering requirements, design, task breakdown and acceptance criteria, human review, execution, then Review/Commit/Push, while Goal takes only the desired outcome and evaluates progress at the end of every round, continuing automatically until met. Two scaled cases: building Qoder with Qoder (10 people, 3 weeks, 500,000 lines of agent code merged into a 4-million-line legacy system, 99% agent-generated, still in production at v1.4.0 with zero incidents; the method is a cognitive base plus Ultra Spec plus Experts cross-review plus a verifier agent filtering hallucinated issues, with humans only deciding SLO definitions and irreversible operations, and each person driving 20-plus Experts tasks a day); and AutoSDK for AMap in-car systems across 20-plus repositories and over a million lines, where the strict first-pass rate went from 37.3% to 61.5% (problem framing cites KoCo-Bench / arXiv:2601.13240v3: general coding reaches 90% Pass@1 while domain code generation reaches only 8.9%). Boundaries: the client and knowledge engine are closed; every scaled number comes from official cases and vendor self-reporting, and self-evidence from a product about itself carries methodological self-interest, none of it independently reproduced; Experts cost per unit is clearly above a single agent (median about 75 versus about 50 Credits) and Credits reset each cycle rather than accumulating. Confidence C (vendor-claim).

500,000 行 · 99% agent 生成10 人 3 周并入 400 万行遗留系统(厂商案例)Vendor Claim · 2026

ProductAlibabaSite Repo

World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal

HKUST(GZ), CUHK and Knowin AI present World Action Agent (WAA), a multi-agent harness that changes what the VLM sees and how its decisions take effect — rather than the VLM itself — so a general-purpose VLM can pilot a robot with basic tools (point, drag, preview, execute), making every decision inside one visual action workspace. Three properties: Contact views, whose camera parameters are solved from interaction-region visibility under occlusion, framing compactness, view redundancy and stability, with the feasible set constraining the two views to orthogonal horizontal projections so any alignment error can be read along two independent directions — requiring only a base-frame point cloud, so the perception source (simulation, fused RGB-D, or VGGT reconstruction) is irrelevant; action rehearsal, where each action is an editable proposal planned by cuRobo, overlaid as a translucent robot in every view with a feasibility report, refined by an Imagination Agent in a separate context while the physical scene stays unchanged, and only proposals with executable plans become motion; and in-view correction, where the agent drags from a reference point to the desired location in the Contact view where the error is observed — the reference can be a visible point on the held object, so no conversion into an absolute gripper pose is needed. Skills evolve from expert videos and human Canvas-GUI teaching through Learner, Editor and Reviewer roles under evidence-citing and independent-review constraints. On LIBERO-Pro with Gemini 3.7 Flash, using skills evolved only from LIBERO-90 and frozen before evaluation, WAA reaches a state-of-the-art 75.6% average success, above ASPIRE (72.0%), end-to-end VLAs and the same-backbone Show-Harness (6.7%), scoring 80.0 / 73.3 on the two Spatial splits; an episode costs just 31 model calls, 150 s and $0.1996 versus 120 calls, 874 s and $0.5021 for Show-Harness. The frozen skills transfer to robosuite at 100.0%, and LoRA fine-tuning Qwen3.5-9B on 112 trajectories (1,774 decision steps) as the main agent only raises out-of-domain success from 1.7% to 43.3%.

Yehang Zhang, Haojian Huang, Yifan ChangSep 24, 2026

World Action AgentWAAVLMSep 24, 2026

0:33

CHORUS: One VLA Policy for Robot Collaboration

@LeoKharon · 251 views · 2026-09-15

Robot CollaborationMulti-agentVLA

1:34

Cursor Ships Projects: One Persistent Thread, a Coordinator Agent, and Subagents

@cursor_ai · 229 views · 2026-09-10

Coding AgentAgent orchestrationMulti-agent

Graph Engineering: The Complete Guide to Building Multi-Agent AI Systems

The hard problem in multi-agent systems is not making one agent smarter, but deciding how work itself should move. This long-form guide introduces Graph Engineering: use the dependency test to expose fake dependencies, measure latency by critical path instead of total steps, compress deterministically before reasoning, give verifiers a falsification objective, model human approval as an edge rather than a node, freeze rules that sit outside optimization, and adopt five canonical graph shapes plus a paste-ready graph spec template — along with clear criteria for when NOT to build a graph at all.

BLOG

Multi-agentGraph engineeringOrchestrationLLMAgent orchestration

0:08

Marope: multi-agent RL for robot rope jumping

@ErenChenAI · 193 views · 2026-08-12

MaropeLAMDAMulti-Agent RL

1:17

Multi-Agent CAD: text-to-3D open source

@xyz2maureen · 162 views · 2026-08-06

CADMulti-agent3D Generation

Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning

In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representation learning-based approaches enable decentralized agents to learn messages grounded in their own observations, but they rely only on current observations and cannot convey information accumulated over time. We propose Dreamer-CPC, a decentralized model-based MARL method that integrates message learning based on Collective Predictive Coding (CPC) into the world model of DreamerV3. Each agent independently maintains a world model and a message module, and infers and exchanges messages from the latent states of the world model that reflect the history of past observations and actions. We evaluated Dreamer-CPC in two environments: Observer, a non-cooperative information-sharing task, and CatchApple, a newly introduced task in which task-relevant observations are temporarily missing. In both environments, Dreamer-CPC outperformed IPPO-CPC, an existing CPC-based method that generates messages from current observations, as well as no-communication baselines. In particular, in CatchApple, Dreamer-CPC achieved 4 to 5 times the episode return of IPPO-CPC, demonstrating effective coordination where other methods fail due to missing observations. These results suggest that communication grounded in the latent dynamics of world models can support decentralized decision-making when current observations alone are insufficient.

Taisuke Takayama, Naoto Yoshida, Tadahiro TaniguchiJul 22, 2026

DreamerWorld ModelsMulti-agentJul 22, 2026

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing autoregressive video diffusion pipelines carry forward observation history as conditioning context, which makes shared state difficult to maintain in multi-agent and multi-view settings. We present WorldWeaver (W^2), a streaming multi-agent video diffusion model that augments rollout with cross-agent world state registers: learnable tokens that store shared world information, track individual agent status, and are dynamically updated after each generated chunk. We ground these registers with supervision signals spanning individual agent status, global state views including bird's-eye views, and scene text. We further improve the architecture with a Mixture-of-Transformers design that uses separate weights for world state modeling and visual frame modeling. Extensive experiments in two-agent Minecraft video generation show that explicit world-state modeling improves logical consistency and generation quality.

Sicheng Mo, Yuheng Li, Ziyang LengJul 23, 2026

World ModelsMulti-agentDiffusion modelsJul 23, 2026