Open sourcePython · ≈86k stars · MIT
DeerFlow
ByteDance's long-horizon SuperAgent harness.
DeerFlow is ByteDance's open-source 'SuperAgent' harness for long-horizon work — research, coding and content creation coordinated with sandboxes, memory and report generation. One of the highest-starred agent frameworks out of China.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- DocsMIT-licensed 2.0 ground-up rewrite with sandboxes, memory, skills, subagents and a message gateway for long tasks that run for minutes to hours.[1]
- DocsSandbox modes cover local host execution, Docker containers and Kubernetes pods via a provisioner service.[1]
- MetadataBacked by ByteDance with a large following (about 85k stars; v2.1.0 in Sept 2026).[1]
Cons
- DocsHeavyweight: at least 4 vCPU and 8 GB RAM for local evaluation (8 vCPU and 16 GB for a long-running server), plus Python 3.12+, Node 22+, uv, pnpm and nginx.[1]
- DocsThe README warns that the AIO sandbox with the Docker socket gives the gateway host root-equivalent access; production defaults to a single gateway worker unless you add Postgres and Redis.[1]
- DocsThe README "strongly recommends" models from ByteDance Volcengine's Coding Plan (Doubao-Seed-2.0-Code, DeepSeek v3.2, Kimi 2.5).[1]
- User reportsSkeptics say its community showcase is unimpressive and that a single-agent system can do just as well.[1]
- Best for
- Teams experimenting with long-horizon research or coding agents who can run a full multi-service stack.
- Watch out for
- On Windows it needs Git Bash (native cmd and PowerShell are unsupported); read the security notice before exposing the gateway or mounting the Docker socket.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Engineer
Core maintainer, DeerFlow
Harness engineering
Engineer
Co-author of DeerFlow, ByteDance
Multi-agent orchestration
Activity
- Last push
- · yesterday
- Latest release
- v2.2.0
· 2w ago - Last 90 days
- 2 releases
v2.2.0DeerFlow 2.2.0
· 2w agoDeerFlow 2.2.0 DeerFlow 2.2 turns the 2.1 super-agent harness into a deployment-grade platform with a focus on operating at scale and delegating with trust: scheduled tasks grow into goal-driven workflows with fair multi-owner execution, every subsystem from IM channels to…
v2.1.0v2.1.0 Release
· 8w agoDeerFlow 2.1.0 DeerFlow 2.1 builds on the 2.0 super-agent harness with a focus on trust, scale, and operability: verifiable agent execution, durable batch delegation, pluggable memory backends, four new sandbox providers, an out-of-tree extension system, and enterprise-grade…
v2.0.0DeerFlow 2.0.0 released
· 4mo agoDeerFlow 2.0.0 DeerFlow 2.0 is a ground-up rewrite around a "super agent" harness that orchestrates sub-agents, persistent memory, sandboxed execution, and an extensible skills/tools system. It shares no code with the 1.x line, which lives on the main-1.x branch. This release…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
Neighbours on the workbench
TypeScript · ≈395k stars · MIT
openclaw/openclaw
The viral open-source personal AI assistant that really does things.
Maintained by OpenClaw Foundation
v2026.11.6releasedTypeScript · ≈285k stars · MIT
deepseek-ai/deepseek-harness
Everything is a Plugin — DeepSeek's open agent harness.
Maintained by DeepSeek
dsh-v0.2.2-rc.5 prereleasedTypeScript · ≈212k stars · Sustainable Use License (fair-code; GitHub reports NOASSERTION)
n8n-io/n8n
Fair-code workflow automation platform with native AI capabilities.
Maintained by n8n-io
n8n@1.123.100releasedConnections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- ByteDanceOrganisation
Mentioned in · 1
- Harness Engineering: Build AI Agents That Work in ProductionEvent · 2026-11-14
