deer-flow is an agent framework for AI builders who want a real project they can inspect instead of a black-box demo. The public repository describes it as: An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. That makes it useful for teams evaluating whether the workflow fits their agents, coding loop, or develop
Cross-referenced across 55 tracked directories
#2867
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
10/28/2026
First Seen
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
cdw0424
Sneakoscope Codex: update-aware, database-safe Codex CLI harness with multi-agent Team orchestration, Ralph no-question execution, autoresearch-style loops, and H-Proof gates.
...moreidoavidan
Agent framework SDK for building autonomous agents on the Ziggs platform
GitHub Actions
The deterministic core that runs a workflow script. It is a **vm-realm script runtime** plus a small DSL (`agent()`, `parallel()`, `pipeline()`, …), a resume journal, a token budget, and optional git-worktree isolation. It drives subagents **only** throug
...moreMicrosoft Foundry Responses container protocol v2.0.0 server. Independent of the Agent Framework.