PulseGateIndexCategoriesUpdatesLive intelligence on AI-era software— indexed in the last hour
Coverage—projects tracked
Freshness—newest entry
Cadence—last week average · — today
Index9 markets86 categories
PulseGate

Live intelligence on the AI-era software market — apps, models, agents and infrastructure.

Most of it never reaches an official store. PulseGate maps the whole market — every category, worldwide — and measures how it moves: what’s launching, what’s gaining, what’s going quiet.

FollowGitHubX (Twitter)LinkedIn
Platform
All AppsFull IndexCategoriesIndustry UpdatesData SourcesCoverage RulesGlossaryEmbed Widget
Support
Help CenterSubmit your projectReport an Issue
Company
AboutDimaxiaPress & DataContactPlatform Status
Legal
PrivacyTermsDisclaimer
Dimaxia · Dymaxio s.r.o. · Prague, Czechia · © 2026WatchlistSitemapSystem status
PulseGateINinfiltr
Visit↗
Skip to content
  1. Index›
  2. Autonomous agents & workflows›
  3. infiltr
← Back to the index
IN

infiltr

PyPI·Infrastructure

infiltr is an open-source command-line tool that uses reinforcement learning to perform adversarial red-teaming on large language model (LLM) systems. It helps AI security researchers and developers identify and address vulnerabilities such as prompt injection and other attacks.

Open SourceMITCLI
Visit PyPI↗
3stars
5features
2026since

Overview

5 features

infiltr is an Autonomous agents & workflows project. It focuses on testing and identifying vulnerabilities in LLM systems using adversarial red-teaming techniques. It is built as an open-source project for AI security researchers and developers. infiltr is open source under the MIT license. It ships for the command line.

It is developed by sushaan-k, and it first shipped in 2026. The project is developed in the open on GitHub with 13 commits in the last 90 days. Among its 5 catalogued features are red teaming, prompt injection testing, and reinforcement learning.

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

  • ✓Red teaming
  • ✓Prompt injection testing
  • ✓Reinforcement learning
  • ✓Security evaluation
  • ✓LLM integration
Tags
red-team-agentllm-securityprompt-injection
AI capabilities
Code
Weights: Open

Built with & integrations

AI providers
openai
Runs on
CLI

Trust & compliance

License
MIT
Verified signals
✓HTTPS✓Open Source✓Free tier✓GitHub · ★ 3✓Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed29 Jun · 13:42 UTC
    Listing verified against its public source
    Source: PulseGate · Open ↗

Frequently asked questions about infiltr

What is infiltr?
Infiltr focuses on testing and identifying vulnerabilities in LLM systems using adversarial red-teaming techniques. It is catalogued under Autonomous agents & workflows on PulseGate.
Who is infiltr for?
infiltr is an open-source project built for AI security researchers and developers.
Is infiltr free?
Yes — infiltr is open source under the MIT license and free to use.
What platforms does infiltr run on?
infiltr runs on the command line.
Is infiltr still active?
The GitHub repository shows 13 commits in the last 90 days.
What are alternatives to infiltr?
Similar projects tracked by PulseGate include chitta-bridge, Bosun, and falcon-limitless-agent.chitta-bridgeBosunfalcon-limitless-agent
Who develops infiltr?
infiltr is developed by sushaan-k.
How long has infiltr been around?
infiltr first shipped in 2026.

At a glance

Platforms
Cli
Languages
English
Open source
Yes · ★ 3
License
MIT
Built for
AI security researchers and developers
Model
Open source
Solves
Testing and identifying vulnerabilities in LLM systems using adversarial red-teaming techniques.

Registered as

GitHub
sushaan-k/phantom
PyPI
infiltr

Developer

sushaan-k
Solo developer
↗ GitHub

Open source

View on GitHub →
Stars
3
Forks
0
Open issues
0
Last commit
3 Jun 2026
Commits 90d
13
Contributors
1
Authorship
Solo
Default branch
main

Live coverage

Identity confidence
Low · 64
Indexed
29 Jun 2026
Lifecycle
Unverified
Last seen
29 Jun 2026
Identity audit (12)
Slug
infiltr-pypi-org
Verification state
Indexed for public listing
Listing state
Listed: yes
Index status
Included in index
Latest evidence snapshot
29 Jun 2026
Timeline basis
Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from
Written by a language model from the project's public pages.
Category from
Assigned by a language model.
Summary from
Written by a language model from public pages.
Languages from
Detected by a language model from page content.
Last updated
29 Jun 2026
Canonical URL
https://pypi.org/project/infiltr

Ship this? Send a correction — no account, and you get a link to follow it.

Also in Autonomous agents & workflows

Same category — not a similarity match

  • CHchitta-bridgegithub.com
  • BOBosunbosun.engineer
  • FAfalcon-limitless-agentpypi.org
  • BEbeddelbeddel.com.br
  • CCcc-plugin-to-codexgithub.com
  • PRProxyClawproxyclaw.ai