Agentpoison
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
Updated
✨ Try AgentScout's free AI image generator →Good for: working with documents, memory for agents, agent security and safety, security testing
Use cases
About Agentpoison
Agentpoison is listed in our agent infra category and is aimed at builders. [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning" Pricing, as the maker states it: Open source. Maturity: Active. We last checked the official link on 2026-11-11.
Agentpoison at a glance
- Category: Agent infra
- Built for: Developers and teams building with AI agents
- Pricing: Open source (as the maker states it)
- GitHub: AI-secure/AgentPoison · 255 stars (as of Nov 11, 2026)
- Official site: billchan226.github.io/AgentPoison
- Listed on AgentScout: Nov 11, 2026
Agentpoison FAQ
What is Agentpoison?
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
How much does Agentpoison cost?
Agentpoison's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Where can I find Agentpoison's source code?
On GitHub at AI-secure/AgentPoison, which had 255 stars as of Nov 11, 2026.
What are alternatives to Agentpoison?
Similar tools include Mnemon, Reevo, Sotopia, AgentLucidity, Agently Daily News Collector and Shadeform.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
Agentpoison ratings and reviews
Be the first to rate Agentpoison: tap 1 to 5 stars below. A written review is optional.
Agentpoison alternatives
Other agent infra tools in our directory. See all agent infra tools →
Mnemon
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime
Reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
Sotopia
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
AgentLucidity
AgentLucidity collects practical knowledge and playbooks from real AI agent runs so builders can reuse what worked.
Agently Daily News Collector
An open-source LLM based automatically daily news collecting workflow showcase powered by Agently AI application development framework.
Shadeform
Shadeform is a marketplace for on-demand GPUs across more than 30 cloud providers, now with an official CLI and MCP server. AI agents can compare prices, launch and manage GPU instances and scale inference through one API, instead of you signing up to each cloud separately.
Get your badge
Built Agentpoison? Optional. Showing this badge does not change your rank or earn a Featured spot. It links to this page. About badges