中文
~/home / Show HN
Show HN

Open-Kritt – Open-source infrastructure for AI-based security research

Open-Kritt – Open-source infrastructure for AI-based security research is a skill AI agent for Support researchers in building and testing AI safety models. Pricing: not stated on the product page. As of 2026-09-12, KanonAgent records 2 upvotes. First indexed by KanonAgent on 2026-07-21.
Open-source infrastructure for AI security research, enabling researchers to build and test AI safety models collaboratively.
Open-Kritt – Open-source infrastructure for AI-based security research — official preview image
2 upvotes
Tracked by Kanon since Jul 21, 2026
no signal yet
status
16/100
momentum · conf 0.53
20d
tracked since 2026-08-22
8
evidence records

No signal event on file yet — status is unknown, not "quiet".

📈 Timelinewhat changed, and when
🔎 Known / Unknown 11 of 23 fields unknown
Machine-callable— unknown —
Open source1 inferred 1 quote(s)
Self-hostable1 inferred 1 quote(s)
Bring your own key1 inferred 1 quote(s)
Autonomy level2 inferred 2 quote(s)
Pricing model— unknown —
Integrationscodex,claude,openai,anthropic,openrouter inferred 2 quote(s)

“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.

🤖 Agent teardown · skill
Job to be doneSupport researchers in building and testing AI safety models
AutonomyL2 · tool-calling(evidence: "analyze remote or local repositories and their dependencies …")
Who it is forAI security researchers
Prerequisitesopen source · self-hostable · bring your own API key
Integrationscodex · claude · openai · anthropic · openrouter
Why it matters

Fills a critical gap in AI safety research infrastructure by offering a reusable, open platform with strong ecosystem potential.

Evidence quotesverbatim, from the product’s own materials

“public GitHub repository (README fetched)”— structural
“open-source, self-hosted security research platform”— readme
“Bring your own model access”— readme
“analyze remote or local repositories and their dependencies with Codex”— readme
“Build workflows — chain focused prompts into reusable security research playbooks.”— readme
“analyze remote or local repositories ... with Codex or Claude Code”— readme
Signal source: Show HN
Visit official site →
📛 Official badgefor your site / README
Open-Kritt – Open-source infrastructure for AI-based security research badge
Building Open-Kritt? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
Share on X
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.

FAQ

What is Open-Kritt?

Open-source infrastructure for AI security research, enabling researchers to build and test AI safety models collaboratively.

What does Open-Kritt do?

Support researchers in building and testing AI safety models

Why does Open-Kritt matter?

Fills a critical gap in AI safety research infrastructure by offering a reusable, open platform with strong ecosystem potential.

Is Open-Kritt open source?

Yes — Open-Kritt is open source.

Can I self-host Open-Kritt?

Yes — Open-Kritt can be self-hosted.

What does Open-Kritt integrate with?

codex,claude,openai,anthropic,openrouter

How popular is Open-Kritt?

As tracked by KanonAgent: 2 upvotes (first indexed 2026-07-21).

What are the best Open-Kritt alternatives?

Similar AI agents tracked by KanonAgent: ECC, open-design, deer-flow, Agent-Reach, ruflo, career-ops.

Open-Kritt – Open-source infrastructure for AI-based security research alternatives — similar AI agents

ECCopen-designdeer-flowAgent-Reachruflocareer-ops

Where this fits — browse the same shelf

AI Agent Skills & PluginsAI agents that work with OpenAI CodexAI agents that work with ClaudeAI agents that work with OpenAISelf-hosted & open-source AI agents