jev-guard
Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.
Details
- External ID
- 1374583864
- Source
- GITHUB
- Company
- —
- Product
- jev-guard
- Website domain
- github.com
- Launched
- Sept. 17, 2026
- Cohort
- —
- Upvotes
- 18
- Upvotes percentile
- 0.5655905713553676
- Tags
- ai-agents, claude-code, codex, cursor, gemini-cli, hooks, jev, opencode, prompt-injection, security
- Fetched at
- Sept. 21, 2026, 5:02 p.m.
- Updated at
- Sept. 21, 2026, 5:02 p.m.
Enrichment
- Theme
- ai coding agents and tooling
- Vertical
- Security
- Function
- Compliance & governance
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- security guardrails for coding agents
- Manually corrected
- False
Could you build this?
Partial The CLI/agent wrapper and policy execution hooks are straightforward to implement, but robust real-time prompt injection detection and accurate dynamic security risk scoring are unsolved security challenges.
What it would actually take: The core tool acts as a proxy or middleware intercepting tool calls and agent responses across various coding assistant protocols (MCP, language server/CLI hooks). The challenging component is the security engine: detecting obfuscated prompt injections and evaluating security risk without high false positive rates, which requires specialized ML classifiers or tailored heuristic rule engines trained on adversarial attack vectors.
Competitors
Other products that read as similar to this one — 214 launches clear the similarity bar, closest 8 shown.
Attention rank: #136 of 215 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 302 days after the earliest competitor.
- pi-jev-auto-mode · github · 2026-09-17 · 20 upvotes · similarity 0.62
- Auto Mode by Claude Code · ph · 2026-03-25 · 514 upvotes · similarity 0.57
- jev-code · github · 2026-09-19 · 13 upvotes · similarity 0.53
- System 1 agents · ph · 2026-09-25 · 2 upvotes · similarity 0.47
- jevx · ph · 2026-09-25 · 2 upvotes · similarity 0.46
- jev-cli · github · 2026-09-19 · 25 upvotes · similarity 0.46
- JevForAgents · ph · 2026-09-25 · 59 upvotes · similarity 0.45
- jev-browser · github · 2026-09-23 · 103 upvotes · similarity 0.45
Other launches for this product
Same idea, different domain
Nobody's really built a compliance & governance tool for Media & entertainment yet.