AI Agent

SHACKLE

SHACKLE is a runtime governance layer and conformance standard for autonomous AI agents, enforcing guardrails, budget/loop limits, and policy constraints in real time.

What is SHACKLE?

SHACKLE (SHACKLE Protocol 1.0) is an open-source governance protocol and policy-decision daemon for autonomous AI agents. It mediates every agent tool call in real time, enforcing circuit breakers for budget, repetitive calls, timeouts, and tool call limits, and provides a verifiable conformance standard (SP/1.0) with hash-checked fixtures. It includes a human-in-the-loop (HITL) console for interactive control.

SHACKLE vs Similar AI Tools

Pricing ModelFree, Custom PricingCustom PricingFree, Free Trial, PaidFree
Free Credits
Key Features
  • Loop of Death prevention via identical sequential tool call detection
  • Real-time budget enforcement with client-side token tracking
  • Execution timeouts to prevent hung threads on dead APIs
  • Natural language agent creation
  • Automated execution plan generation
  • Human approval for write actions
  • Session Builder with templates (onboarding, demo, training, support)
  • Instant Expert short sessions (up to 10 min) and Structured Sessions (up to 60 min)
  • Knowledge-base digest for AI context
  • 11 system classes with 247 verified records
  • Ranked by maintained adoption (never by sponsorship)
  • Curated by hand and refreshed weekly
Pros
  • Prevents runaway costs and infinite loops in AI agents
  • Easy one-line integration with popular frameworks
  • Bridges the gap between AI adoption and security compliance
  • No-code agent building accessible to subject matter experts
  • Voice-enabled AI agent for natural interactions
  • Works across multiple surfaces: in-app, meetings, internal tools
  • Comprehensive index of agents and infrastructure
  • Rankings based on community adoption, not sponsorship
Cons
  • AGPLv3 license requires open-sourcing for closed-source use
  • HITL console not suitable for headless production APIs
  • Product is in early access with limited integrations
  • Requires enterprise environment for full benefit
  • Pricing based on credits per session, which may be complex
  • Free trial is limited in session volume and duration
  • Focuses mainly on open-source projects
  • No user reviews or ratings
Best For
  • Developers building autonomous AI agents
  • Teams needing runtime safety and cost controls
  • Enterprise teams needing compliant AI adoption
  • Security-conscious organizations wanting to deploy AI agents safely
  • Customer success and support teams
  • Sales and solution engineering teams
  • Developers comparing AI agent tools
  • Technical decision-makers selecting agent infrastructure

How to use SHACKLE?

  1. 1Install via pip install pyshackle or clone from source.
  2. 2Import from shackle import Guard.
  3. 3Decorate your agent workflow function with @Guard(budget=0.25, max_repeat_calls=3, timeout_seconds=180).
  4. 4Run the function as usual; SHACKLE automatically hooks into the underlying framework (CrewAI, LangGraph, AutoGen, etc.).
  5. 5When a circuit breaker trips, an interactive HITL console appears with Resume/Skip/Abort options.

SHACKLE Key Features

  • Loop of Death prevention via identical sequential tool call detection
  • Real-time budget enforcement with client-side token tracking
  • Execution timeouts to prevent hung threads on dead APIs
  • Human-in-the-loop (HITL) interactive terminal console
  • Verifiable conformance standard (SP/1.0) with 15 hash-checked fixtures
  • First-class integrations with LiteLLM and AutoGen
  • 100% client-side, no telemetry or phone-home
  • One-line installation with no refactoring of agent topology

SHACKLE Use Cases

  • Local development and debugging of AI agents
  • CLI agents and supervised workflows with HITL control
  • Cross-framework governance across CrewAI, LangGraph, and AutoGen
  • Budget enforcement to prevent runaway API costs
  • Iterative testing and catching loops early in development

SHACKLE Pricing & Free Credits

SHACKLE currently operates on a Free, Custom Pricing model.

Free Tier

AGPLv3 (Free)

Free

Open-source license for individual developers, hobbyists, and open-source projects. V1 includes all core features.

Paid Plans

Commercial License

Contact for Pricing

For closed-source commercial products, SaaS, or enterprise deployments. Includes white-labeling, priority support, and custom integration assistance.

V2 Enterprise (Optional)

Contact for Pricing

Adds distributed state, Postgres audit logs, remote HITL control, and commercial licensing for production deployments.

AGPLv3 (Free)

Free

Open-source license for individual developers, hobbyists, and open-source projects. V1 includes all core features.

Commercial License

Contact for Pricing

For closed-source commercial products, SaaS, or enterprise deployments. Includes white-labeling, priority support, and custom integration assistance.

V2 Enterprise (Optional)

Contact for Pricing

Adds distributed state, Postgres audit logs, remote HITL control, and commercial licensing for production deployments.

SHACKLE Pros & Cons

Pros

  • Prevents runaway costs and infinite loops in AI agents
  • Easy one-line integration with popular frameworks
  • Open standard with verifiable conformance testing
  • Fully client-side with no external dependencies or telemetry

Cons

  • AGPLv3 license requires open-sourcing for closed-source use
  • HITL console not suitable for headless production APIs
  • V2 enterprise features require separate contact for pricing

What is SHACKLE best for?

  • Developers building autonomous AI agents
  • Teams needing runtime safety and cost controls
  • Organizations seeking verifiable governance for compliance

SHACKLE FAQ

Top free alternatives to SHACKLE

Agentcard logo

Agentcard provides agent-friendly card issuing and payment infrastructure for AI agents, enabling 5-minute setup and autonomous purchases.

Free
YAGNI logo

Manage AI agent teams like human teams with responsibilities, numbers, commitments, and approvals across your business tools.

Free
Oodle AI logo

Oodle AI provides agent observability with fast trace search, S3-based storage, and out-of-the-box insights to detect silent failures in AI agents.

Free
Scarlett logo

Scarlett is an AI coworker that lives in Slack, connecting to over 3,000 tools to automate tasks, generate reports, and execute real work for your team.

Free
Acti logo

Acti is the world's first agentic keyboard that transforms any text field into an action layer, letting users type their intent and long-press to execute actions across apps.

Free
Opper AI logo

A unified AI gateway providing access to 300+ leading models through one EU-hosted, GDPR-compliant API with an OpenAI SDK-compatible interface.

Free
Ogment logo

Ogment is an AI coworker that lives in Slack, proactively automating repetitive tasks and workflows for your team.

Free
ElevenAgents logo

Deploy and customize AI-powered voice and chat agents to automate customer support, sales, and operations across multiple channels.

Free

Best alternatives AI Tools to SHACKLE

Lunen logo

A governed AI agent platform that allows anyone to build agents while ensuring human approval and full audit trails for every action.

Skippr logo

Skippr is a live AI employee that embeds into your product, meetings, and internal tools to drive demos, onboarding, support, and team enablement.

Agent Search Engine logo

An independent, curated index and search engine for AI agents, MCP servers, frameworks, and infrastructure tools, ranked by maintained adoption.

R

Rewisp is an on-device ambient memory for Mac that captures text from your screen and lets you ask anything about your past activity, automatically surfacing promises, changes, and summaries while keeping everything private.

RixLabs logo

Backtest crypto trading strategies by describing them in plain English, directly from Claude, ChatGPT, or any AI agent.

Panguard AI logo

Open-source platform for real-time AI agent security, auditing skills and runtime with community-driven threat rules.

SureWire Beta logo

SureWire Beta is an AI agent validation platform that helps ensure your AI agents are safe and reliable through comprehensive testing.