agentjail

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

LuD1161/agentjail

View on GitHub ↗

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

agentjail grew +6.1% in the last 30 days, ranks 705th of 872 in Evaluation & Guardrails, last commit 58 days ago.

Star trajectory

82 days tracked
2026-08-31105 stars today2026-11-22
Momentum

+6.1% in 30d, above the Evaluation & Guardrails median of +1.4%.

Maintenance

Last commit 58 days ago, staler than the median of 15d.

How it compares in Evaluation & Guardrails

agentjail
105
stars
+6.1% 30d
commit 58 days ago
Evaluation & Guardrails median
235
stars
+1.4% 30d
commit ~15d ago
Leader · impeccable
114.7k
stars
+0.0% 30d
commit today

Ranked 705th of 872 by stars.

Ranked by shared tags, then keywords, then stars
  1. Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets…

    +518 (+332%) in 30d · Committed 2d ago · Go · Apache-2.0

    Shares Evaluation & Guardrails, Tools & Integrations

  2. Project CodeGuard is an open-source, model-agnostic security framework that embeds secure-by-default practices…

    +21 (+5.9%) in 30d · Committed yesterday · Python · Other license

    Shares Evaluation & Guardrails, Tools & Integrations

  3. Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills…

    +53 (+80%) in 30d · Committed today · JavaScript · MIT

    Shares Evaluation & Guardrails, Tools & Integrations

  4. A fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents…

    Committed today · Rust · Other license

    Shares Evaluation & Guardrails, Tools & Integrations

  5. Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A…

    +1k (+34%) in 30d · Committed today · JavaScript · MIT

    Shares Tools & Integrations, Evaluation & Guardrails

  6. Deterministic guardrails that don't break agents

    +46 (+2.9%) in 30d · Committed today · Rust · MIT

    Shares Evaluation & Guardrails, Tools & Integrations

  7. AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions…

    +17 (+1.7%) in 30d · Committed 103d ago · Python · AGPL-3.0

    Shares Evaluation & Guardrails, Tools & Integrations

  8. Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with…

    +54 (+7.0%) in 30d · Committed 18d ago · Python · Apache-2.0

    Shares Evaluation & Guardrails, Tools & Integrations

  9. Tracekit records what your AI agents do, decides each tool call before it runs, and gives you a signed record…

    +649 (+433%) in 30d · Committed today · Python · MIT

    Shares Evaluation & Guardrails, Tools & Integrations

  10. Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data…

    +7 (+1.0%) in 30d · Committed 2d ago · TypeScript · Apache-2.0

    Shares Evaluation & Guardrails, Tools & Integrations

Language
Go
License
Apache License 2.0
Contributors
3
Forks
8
Watchers
0
Open issues
2
Releases
38
Created
2026-06-04
Stars this week
+2

You've seen where agentjail stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain agentjail?

Claim this page to add your own call-to-action.

Claim this page