Skip to content
Back to the index

agent-immune

github.comInfrastructure

PulseGate's liveness check found it on 13 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 28 Jun 2026. How this is checked

agent-immune is an open-source Python package that provides adaptive threat intelligence and security features for AI agents. It includes semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening to protect agent-based systems from evolving threats.

Inferred · not functionally tested

Open SourceApache-2.0CLI
agent-immune preview
Visit github.com
1alternative
5features
2026since

Overview

5 features

Purpose: Protects AI agents from security threats such as prompt injection and output manipulation.

Inferred · not functionally tested

Audience: ai agent developers

Inferred · not functionally tested

Functions: monitoring, data_extraction

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: unknown

Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: github.com. These links do not verify the individual claims.

agent-immune is an AI & LLM security project. Inferred · not functionally tested: It protects AI agents from security threats such as prompt injection and output manipulation. Inferred · not functionally tested: agent-immune is an open-source project aimed at ai agent developers. Basis unknown · not verified: The project is open source (Apache-2.0). Basis unknown · not verified: agent-immune is available on the command line.

denial-web builds and maintains agent-immune, and it first shipped in 2026. The project is developed in the open on GitHub with 28 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are threat intelligence, semantic memory, and output scanning. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Threat intelligence
  • Semantic memory
  • Output scanning
  • Prompt hardening
  • Rate limiting

Topics: Inferred · not functionally tested

Tags
ai-securityprompt-injectionagent-governance
AI capabilities
Text
Weights: Open

JSON profile · Text profile · Access guide

Built with & integrations

Connectors
MCP
Runs on
CLI

Trust & compliance

License
Apache-2.0
Public signals
HTTPSOpen SourceFree tierGitHubActive maintenance

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about agent-immune

What is agent-immune?
Inferred · not functionally tested: Agent-immune protects AI agents from security threats such as prompt injection and output manipulation. It is catalogued under AI & LLM security on PulseGate.
Who should use agent-immune?
Inferred · not functionally tested: agent-immune is an open-source project built for ai agent developers.
Is agent-immune free?
Basis unknown · not verified: Yes — agent-immune is open source under the Apache-2.0 license and free to use.
What platforms does agent-immune run on?
Basis unknown · not verified: agent-immune runs on the command line.
Is agent-immune still active?
PulseGate's liveness check found it on 13 Sep 2026. Its GitHub repository shows 28 commits in the last 90 days.
What projects are similar to agent-immune?
Similar projects tracked by PulseGate include ai-immune, agent-probe-ai, and agentomy-agent.ai-immuneagent-probe-aiagentomy-agent
Who develops agent-immune?
agent-immune is developed by denial-web.
How long has agent-immune been around?
agent-immune first shipped in 2026.

Similar projects

Closest matches by what these projects do