Explore/framework/AgentPoison
A

AI-secure/AgentPoisonActive

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

frameworkPythonMIT
GitHubCompare
Refreshed 2h ago
OverviewActivity52wAlternativesDocs
Stars244
Forks35
HF Downloads—30d
Last commit3d ago
Refreshed2h ago
Project healthActiveLast commit 3d ago.
Production readinessExperimentalGrowing but not yet battle-tested at scale.
Risk notesMITVerify license before production use.
AgentHub Score
75 / 100
Composite score from 6 signals. How we score →
Active project
75Score
Growth
83B+
Activity
90A
Documentation
70C+
Maturity
72C+
Community
83B+
Production
58C
GitHub stars · 71 days observed244 +0.83% / 30d
snapshots
Repository activity · 71 days observedReal snapshots from pushed_at
inactivepushed
2026-07-262026-10-06
Practical assessment
Should you use it?

✓ Best for

  • Multi-agent orchestration
  • Production agentic workflows
  • Stateful long-running tasks

◎ Strengths

  • Stable API
  • Active release cadence
  • Strong GitHub community

✕ Not ideal for

  • Simple single-step automation
  • Teams without Python/ML expertise

⚠ Watch-outs

  • Breaking changes between minor versions
  • Ecosystem lock-in if tightly coupled
Technical details
What's inside
LanguagePython
LicenseMIT
Sourcegithub
Open source✗ No
Commercial use—
Docs—
Demo—
Paper—

AgentHub Score

75
Score 75/100
Above average

Alternatives

E
ECC
274.0k · framework
95
P
ponytail
156.5k · framework
95
C
cc-switch
140.5k · framework
95
G
graphify
124.2k · framework
95
Compare all →

Recent activity

Latest commit 3d ago3d ago
Indexed by AgentHub crawler2h ago
Monitor for new releasesongoing