Xpersona

Crawler Summary

agentbrake answer-first brief

The emergency brake for multi-agent systems. Stop runaway LangChain & CrewAI agents before they burn your budget. πŸ›‘ AgentBrake **The emergency brake for multi-agent systems.** Stop runaway LangChain & CrewAI agents in real time β€” *before* 50 cents turns into $47,000. The install name is agentbrake-sdk; you import it as agentbrake. *A runaway agent racking up cost, stopped the moment it crosses your ceiling, before the bill grows. There's also a $1 that brakes a real LangGraph loop you can run yourself.* --- The problem In Novem Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

agentbrake is best for crewai, multi-agent workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB REPOS, runtime-metrics, public facts pack

CardFactsSnapshotContractTrust
Claim this agent
Agent DossierGITHUB REPOSSafety: 66/100

agentbrake

The emergency brake for multi-agent systems. Stop runaway LangChain & CrewAI agents before they burn your budget. πŸ›‘ AgentBrake **The emergency brake for multi-agent systems.** Stop runaway LangChain & CrewAI agents in real time β€” *before* 50 cents turns into $47,000. The install name is agentbrake-sdk; you import it as agentbrake. *A runaway agent racking up cost, stopped the moment it crosses your ceiling, before the bill grows. There's also a $1 that brakes a real LangGraph loop you can run yourself.* --- The problem In Novem

OpenClawself-declared

Public facts

5

Change events

1

Artifacts

0

Freshness

Oct 9, 2026

Verifiededitorial-contentNo verified compatibility signals1 GitHub stars

Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 10/9/2026.

1 GitHub starsTrust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Oct 9, 2026

Vendor

Marcoschulz7

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 10/9/2026.

View Source

Setup snapshot

  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Marcoschulz7

profilemedium
Observed Oct 9, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed Oct 9, 2026Source linkProvenance
Adoption (1)

Adoption signal

1 GitHub stars

profilemedium
Observed Oct 9, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub Β· GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB REPOS

Extracted files

0

Examples

6

Snippets

0

Languages

python

Executable Examples

bash

pip install agentbrake-sdk

python

from agentbrake import LangChainBrakeMiddleware
from langchain.agents import create_agent

agent = create_agent(
    model, tools=tools,
    middleware=[LangChainBrakeMiddleware(max_cost_usd=2.00, repeat_tool_limit=5)],
)

python

from agentbrake import LangChainBrakeMiddleware, AgentBrakeError
from langchain.agents import create_agent

agent = create_agent(
    model, tools=tools,
    middleware=[LangChainBrakeMiddleware(max_cost_usd=2.00, repeat_tool_limit=5, max_steps=30)],
)

try:
    agent.invoke({"messages": [("user", "...")]})
except AgentBrakeError as e:
    print(f"Stopped safely: {e.reason}")

python

from agentbrake import LangChainBrake, AgentBrakeError

brake = LangChainBrake(
    max_cost_usd=2.00,
    repeat_tool_limit=5,
    max_steps=30,
)

try:
    agent_executor.invoke({"input": "..."}, config={"callbacks": [brake]})
except AgentBrakeError as e:
    print(f"Stopped safely: {e.reason}")

python

from agentbrake import CrewAIBrake, AgentBrakeError

CrewAIBrake(max_cost_usd=3.00, repeat_tool_limit=5).install()

try:
    crew.kickoff()
except AgentBrakeError as e:
    print(f"Crew stopped safely: {e.reason}")

text

[AgentBrake] step 1: web_search Β· running cost $0.4000
[AgentBrake] step 2: web_search Β· running cost $0.8000
[AgentBrake] step 3: web_search Β· running cost $1.2000
[AgentBrake] step 4: web_search Β· running cost $1.6000
[AgentBrake] ⚠️  approaching cost limit (1.60 of 2.0)
[AgentBrake] step 5: web_search Β· running cost $2.0000
[AgentBrake] πŸ›‘ STOPPED β€” cost ceiling reached ($2.00 β‰₯ $2.00)
  steps=5 tool_calls=5 llm_calls=5 cost=$2.0000 elapsed=6.2s

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

The emergency brake for multi-agent systems. Stop runaway LangChain & CrewAI agents before they burn your budget. πŸ›‘ AgentBrake **The emergency brake for multi-agent systems.** Stop runaway LangChain & CrewAI agents in real time β€” *before* 50 cents turns into $47,000. The install name is agentbrake-sdk; you import it as agentbrake. *A runaway agent racking up cost, stopped the moment it crosses your ceiling, before the bill grows. There's also a $1 that brakes a real LangGraph loop you can run yourself.* --- The problem In Novem

Full README

πŸ›‘ AgentBrake

The emergency brake for multi-agent systems. Stop runaway LangChain & CrewAI agents in real time β€” before 50 cents turns into $47,000.

pip install agentbrake-sdk

The install name is agentbrake-sdk; you import it as agentbrake.

AgentBrake halting a runaway agent at a cost ceiling

A runaway agent racking up cost, stopped the moment it crosses your ceiling, before the bill grows. There's also a no-API-key example that brakes a real LangGraph loop you can run yourself.

The problem

In November 2025, four LangChain agents entered an infinite loop. They ran for 11 days. The bill was $47,000. Nobody noticed until it was over.

This is not rare. Autonomous agents fail expensively rather than loudly:

  • An agent calls the same tool 14,000 times with identical arguments.
  • A planner expands one simple task into dozens of high-context subagent calls.
  • A reasoning loop never hits its stopping condition and runs all night.

Observability tools record this. They don't stop it. By the time the alert fires β€” or someone reads it β€” the money is gone. The gap between "the alert fired" and "the run stopped" is exactly where the damage compounds.

AgentBrake closes that gap. It intercepts, not just observes.

How it works

AgentBrake hooks into your agent's execution and watches every step in real time. When a run crosses a limit you set, it raises a clean exception that halts the agent before the next expensive call goes out.

from agentbrake import LangChainBrakeMiddleware
from langchain.agents import create_agent

agent = create_agent(
    model, tools=tools,
    middleware=[LangChainBrakeMiddleware(max_cost_usd=2.00, repeat_tool_limit=5)],
)

That's it. One line.

What it catches

| Runaway pattern | How AgentBrake stops it | |---|---| | Identical-tool loops (same call, same args, over and over) | repeat_tool_limit β€” trips after N identical calls in a row | | Cost blowouts (the $47k overnight run) | max_cost_usd β€” a hard ceiling, enforced live as tokens are spent | | Endless reasoning (no stopping condition) | max_steps β€” caps total reasoning steps | | Tool-call storms | max_tool_calls β€” caps total tool invocations | | Hung runs | max_duration_s β€” wall-clock ceiling |

It warns at 80% of any limit, and stops at 100%.

LangChain

LangChain has two agent stacks, and they intercept differently β€” AgentBrake ships the right tool for each.

LangChain 1.x (create_agent / LangGraph) β€” use the middleware. It runs inside the agent graph, so it can actually halt the run:

from agentbrake import LangChainBrakeMiddleware, AgentBrakeError
from langchain.agents import create_agent

agent = create_agent(
    model, tools=tools,
    middleware=[LangChainBrakeMiddleware(max_cost_usd=2.00, repeat_tool_limit=5, max_steps=30)],
)

try:
    agent.invoke({"messages": [("user", "...")]})
except AgentBrakeError as e:
    print(f"Stopped safely: {e.reason}")

Classic AgentExecutor (LangChain 0.x) β€” use the callback:

from agentbrake import LangChainBrake, AgentBrakeError

brake = LangChainBrake(
    max_cost_usd=2.00,
    repeat_tool_limit=5,
    max_steps=30,
)

try:
    agent_executor.invoke({"input": "..."}, config={"callbacks": [brake]})
except AgentBrakeError as e:
    print(f"Stopped safely: {e.reason}")

CrewAI

from agentbrake import CrewAIBrake, AgentBrakeError

CrewAIBrake(max_cost_usd=3.00, repeat_tool_limit=5).install()

try:
    crew.kickoff()
except AgentBrakeError as e:
    print(f"Crew stopped safely: {e.reason}")

Live cost visibility

Every run prints where your money is going, step by step:

[AgentBrake] step 1: web_search Β· running cost $0.4000
[AgentBrake] step 2: web_search Β· running cost $0.8000
[AgentBrake] step 3: web_search Β· running cost $1.2000
[AgentBrake] step 4: web_search Β· running cost $1.6000
[AgentBrake] ⚠️  approaching cost limit (1.60 of 2.0)
[AgentBrake] step 5: web_search Β· running cost $2.0000
[AgentBrake] πŸ›‘ STOPPED β€” cost ceiling reached ($2.00 β‰₯ $2.00)
  steps=5 tool_calls=5 llm_calls=5 cost=$2.0000 elapsed=6.2s

Pricing built in

AgentBrake ships with current pricing for GPT-4o, GPT-4, Claude (Opus/Sonnet/Haiku), and Gemini, so cost ceilings work out of the box. Override anytime with your own rates.

Why not just set a provider spend cap?

Provider caps are monthly and account-wide β€” they fire after the damage, across everything. AgentBrake is per-run and in-process β€” it stops this agent now, before the next call. It's the difference between a smoke alarm and a sprinkler.

License

FSL-1.1-MIT (Functional Source License). Free to use, modify and self-host for any purpose, except building a competing commercial product or service. Each release converts automatically to the MIT license two years after it ships. (Versions 0.1.0 and 0.1.1 were released under MIT and stay MIT.)

Because AgentBrake runs in-process (no proxy, no gateway), your prompts and data never leave your environment, and the overhead is measured in microseconds. Privacy by design, near-zero added latency.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB REPOS

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation β€’ (~400 MCP servers for AI agents) β€’ AI Automation / AI Agent with MCPs β€’ AI Workflows & AI Agents β€’ MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW
Agent hubMore from this sourceOpenClaw agents
Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T13:47:14.798Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "crewai",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "multi-agent",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Marcoschulz7",
    "href": "https://github.com/marcoschulz7/agentbrake",
    "sourceUrl": "https://github.com/marcoschulz7/agentbrake",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T03:24:49.779Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T03:24:49.779Z",
    "isPublic": true
  },
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "1 GitHub stars",
    "href": "https://github.com/marcoschulz7/agentbrake",
    "sourceUrl": "https://github.com/marcoschulz7/agentbrake",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T03:24:49.779Z",
    "isPublic": true
  },
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-marcoschulz7-agentbrake/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub Β· GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to agentbrake and adjacent AI workflows.