Explore/agent app/OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets
O

Dongsheng Chen, Xiangyu Zhao, Xin Yao, Xuetao Wei/OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent FleetsUnknown

AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, tools, and execution backends operate over shared environments. In such settings, safety becomes a system-level action-governance problem: deciding whether a pending action should be committed given policy-relevant state accumulated across a session. Existing safeguards operate at fragmented boundaries, making it difficult to enforce shared policies over composed action flows across heterogeneous execution paths. We present OpenAgentFlow, a control-plane/action-plane architecture that establishes the action-commit boundary as a shared enforcement interface. GUI, API, tool, and LLM-generated actions are normalized into a common AgentEvent stream and mediated by a shared pre-execution Policy Enforcement Point, while provenance, session state, audit evidence, and updatable policies are maintained outside individual agents. This provides a common governance layer across incompatible executors and allows new policies to take effect without modifying agents, prompts, models, or execution paths. We evaluate OpenAgentFlow through complementary system evaluations spanning controlled action-flow tests, a public external benchmark, policy updates, and real Android execution. On a 300-case controlled suite, OpenAgentFlow achieves 94.00% accuracy and a 95.35% attack-block rate. On the complete 1,220-case AgentDojo-Traj split of TS-Bench, it achieves 97.62% accuracy, 96.59% unsafe-action recall, and a 1.96% safe false-intervention rate. New control-plane rules take effect without modifying protected agents, and the same enforcement path operates across live GUI, API/tool, and LLM-planned Android execution. These results show that a shared action-commit boundary provides a practical basis for system-wide governance across heterogeneous agent execution paths.

agent app
GitHubCompare
Refreshed 2d ago
OverviewActivity52wAlternativesDocs
Stars0
Forks0
HF Downloads—30d
Last commit—
Refreshed2d ago
Project healthUnknownNo activity data.
Production readinessResearch / EarlyBest for exploration and prototyping.
Risk notesUnknown licenseVerify license before production use.
AgentHub Score
55 / 100
Composite score from 6 signals. How we score →
Active project
55Score
Growth
40C
Activity
30C
Documentation
70C+
Maturity
45C
Community
42C
Production
58C
GitHub stars · 1 days observed0 not enough history
snapshots
Repository activity · 1 days observedReal snapshots from pushed_at
inactivepushed
2026-09-042026-09-06
Practical assessment
Should you use it?

✓ Best for

  • Research and experimentation
  • Prototype development
  • Learning agentic patterns

◎ Strengths

  • Active community
  • Open source
  • Well-documented API

✕ Not ideal for

  • Untested at scale without validation
  • Teams without AI/ML expertise

⚠ Watch-outs

  • Review changelog before updating
  • Verify license for commercial use
Technical details
What's inside
Language—
License—
Sourcearxiv
Open source✗ No
Commercial use—
Docs—
Demo—

AgentHub Score

55
Score 55/100
Below average

Alternatives

O
OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
0 · agent app
55
A
A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
0 · agent app
55
S
Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond
0 · agent app
55
U
Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents
0 · agent app
55Compare all →

Recent activity

Latest commit ——
Indexed by AgentHub crawler2d ago
Monitor for new releasesongoing