AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Memory & Context/
jamjet
jamjet logo

jamjet

Active·★ 23·Apache-2.0·Updated 2026-10-11

JamJet is an action-control plane for AI agents that enforces safety policy across hooks, guardrails, MCP gateways, SDKs, and custom runtimes. It blocks unsafe tool calls, requires human approval for risky actions, caps costs, and provides a durable audit trail. One policy file works everywhere, supporting frameworks like Claude Code, OpenAI Agents SDK, LangChain, and more.

#a2a#agent-memory#agent-safety#agentic-ai#ai-agents#ai-governance#ai-safety
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#approval-workflows
$ Install
$ pip install jamjet
↗ Visit site★ GitHub
01

Features

01Block unsafe tool calls at runtime (e.g., database deletes, payments)
02Pause for human approval on risky actions with durable execution
03Cap cost per agent, per run, per project
04Record an append-only audit trail for regulatory review
05Replay or resume crashed runs from the last checkpoint
02

Compatibility

Claude Code
Claude Code Hook
Verified via docs
MCP Client
MCP Shim
Verified via docs
OpenAI Agents SDK (TS)
Tool Guardrail (TS)
Verified via docs
OpenAI Agents SDK (Python)
Tool Guardrail (Python)
Verified via docs
Python SDK
Python SDK + Runtime
Verified via docs
TypeScript SDK
TypeScript SDK + Engine
Verified via docs
03

Quick start

1
$ pip install jamjet
04

Use cases

↳Calling MCP servers or arbitrary tools
↳Writing to a database
↳Sending emails or Slack messages
05

Alternatives

⚡Top VS:
VSsystemprompt-template★29→VSIntercept★32→VSaltk-evolve★131→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
bernstein
★1.4k
→
systemprompt-template logo
systemprompt-template★ 29
AI Governance Infrastructure — local evaluation. The governance layer for AI agents: a single compiled Rust binary that authenticates, authorises, rate-limits, logs, and costs every AI interaction. Self-hosted, air-gap capable, provider-agnostic.
VSCompare→
Intercept logo
Intercept★ 32
The enforcement layer for AI agents. Intercept enforces hard, deterministic limits on what agents can do at the MCP transport layer — before execution.
VSCompare→
altk-evolve logo
altk-evolve★ 131
Self improving agents through iterations
VSCompare→
bernstein logo
bernstein★ 1.4k
Deterministic orchestrator for 30+ CLI AI coding agents. Git worktree isolation, HMAC audit trail, MCP server mode.
VSCompare→
agentic-ai logo
agentic-ai★ 176
This repository serves as a comprehensive knowledge hub, curating cutting-edge research papers and developments across 24 specialized domains
VSCompare→
magic-context logo
magic-context★ 2.4k
Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.
VSCompare→
agoragentic-integrations logo
agoragentic-integrations★ 41
Agent OS integrations for deployed agents: smart routing, execute-first tools, Micro ECF exports, x402 calls, receipts, and Base USDC settlement.
VSCompare→
PrismerCloud logo
PrismerCloud★ 1.4k
Prismer Cloud
VSCompare→
See all alternatives →
jamjet-labs /
jamjet
↗

The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.

23Apache-2.0
Last commit1w ago
StatusActive
CategoryMemory & Context
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit