jes
Open-source guardrails for AI agents powered by decision models like Jev; checks prompts, retrieved content, tool calls and responses for prompt injection, jailbreaks and secret/PII leaks.
Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.
This is 1 of 516 launches in developer tools for AI agents — see how it stacks up on momentum and crowding →
2138 other launches read as similar to this one →
Details
- External ID
- 1394949155
- Source
- GITHUB
- Company
- —
- Product
- jes
- Website domain
- github.com
- Launched
- Sept. 29, 2026
- Cohort
- —
- Upvotes
- 8
- Upvotes percentile
- 0.14045078527754465
- Tags
- ai-agents, ai-security, guardrails, jailbreak, langchain, llm-security, mcp, pii-redaction, prompt-injection, python
- Fetched at
- Oct. 3, 2026, 1:02 a.m.
- Updated at
- Oct. 3, 2026, 1:02 a.m.
Enrichment
- Niche
- developer tools for AI agents
- Vertical
- Security
- Function
- Compliance & governance
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- open source security and prompt injection guardrails for ai agents
- Manually corrected
- False
Could you build this?
Partial Wrapping API middleware for LLM guardrails is doable, but reliable detection of advanced prompt injections, jailbreaks, and zero-day adversarial jailbreak vectors requires dedicated ML classification models and security research.
What it would actually take: A production guardrail system requires low-latency middleware (Python/FastAPI or Rust/Go) deploying specialized, fine-tuned transformer classifiers (e.g., DeBERTa-based injection detectors, regex/NER PII tokenizers) optimized via ONNX/TensorRT to keep latency under 20-50ms. The system requires adversarial training pipelines continuously benchmarked against evasive prompt injection benchmarks, heuristic scanners, and strict semantic validation parsers for tool call schemas.
Competitors
Other products that read as similar to this one — 2138 launches clear the similarity bar, closest 8 shown.
Attention rank: #1637 of 2139 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 335 days after the earliest competitor.
- jevals · github · 2026-09-20 · 83 upvotes · similarity 0.73
- jevwire · github · 2026-09-17 · 15 upvotes · similarity 0.68
- awesome-jev · github · 2026-09-18 · 75 upvotes · similarity 0.67
- jevdo · github · 2026-10-02 · 28 upvotes · similarity 0.62
- jot · github · 2026-09-18 · 19 upvotes · similarity 0.62
- agent-guard · github · 2026-09-28 · 20 upvotes · similarity 0.62
- omo-jev-plugin · github · 2026-09-27 · 24 upvotes · similarity 0.61
- Agent Armor, a Rust runtime for enforcing policies on AI agent actions · hn · 2026-04-17 · 7 upvotes · similarity 0.60
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a compliance & governance tool for Media & entertainment yet.