How should work-ledger be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this skill.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

work-ledger answer-first brief

Agentic monitoring and benchmarking tool. Pluggable into LangChain, CrewAI, LangGraph, PydanticAI. Work Ledger Agent broke after a change? **Record. Replay. Diff.** Find out why. $1 $1 The Problem You changed the model. Or the prompt. Or the retrieval strategy. Now your agent behaves differently and you have no idea why. - *"It was working yesterday, what happened?"* - *"Which step is producing wrong output?"* - *"I can't reproduce the bug from production"* Your logs say the agent ran. They don't say *what it deci Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Freshness

Last checked 4/15/2026

Best For

work-ledger 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 OPENCLEW, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGitHubSafety: 66/100

work-ledger

OpenClawself-declared

Public facts

Change events

Artifacts

Freshness

Apr 15, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Apr 15, 2026

Vendor

Metawake

Artifacts

Benchmarks

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Unpublished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. Last updated 4/15/2026.

View Source

Setup snapshot

git clone https://github.com/metawake/work-ledger.git

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
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

Metawake

profilemedium

Observed Apr 15, 2026Source link Provenance

Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium

Observed Apr 15, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

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 · 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 OPENCLEW

Extracted files

Examples

Snippets

Languages

python

Executable Examples

bash

pip install work-ledger

python

from work_ledger import WorkLedger

ledger = WorkLedger(store="./runs")

# Record a run
with ledger.run(name="my-agent") as run:
    run.record_input({"query": "What's the weather?"})
    
    with run.step("llm-call", kind="model") as step:
        response = "It's sunny, 72°F"  # Your LLM call here
        step.record_output({"response": response})
    
    run.record_output({"answer": response})

# See what was recorded
print(ledger.list_runs()[0].to_dict())

bash

work-ledger diff ./runs <run1> <run2>

text

Comparing runs:
  Expected: abc123... (my-agent)
  Actual:   def456... (my-agent)

Similarity: 58.3%

Output changes:
  ~ answer: "It's sunny..." → "It's cloudy..."

Step changes:
  + retrieve-weather [retrieval]

Metric changes:
  total_tokens: 150 → 460

python

from work_ledger import WorkLedger, wrap_agent, wrap_graph, wrap_chain

ledger = WorkLedger(store="./runs")

# PydanticAI
wrapped = wrap_agent(my_agent, ledger)
result = wrapped.run_sync("Hello!")

# LangGraph  
wrapped = wrap_graph(my_graph, ledger)
result = wrapped.invoke({"messages": [...]})

# LangChain
wrapped = wrap_chain(my_chain, ledger)
result = wrapped.invoke({"question": "..."})

bash

git clone https://github.com/metawake/work-ledger.git
cd work-ledger && pip install -e .

python samples/03_detect_regression.py  # See a diff in action

Docs & README

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

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Full README

Work Ledger

Agent broke after a change? Record. Replay. Diff. Find out why.

Demo

The Problem

You changed the model. Or the prompt. Or the retrieval strategy. Now your agent behaves differently and you have no idea why.

"It was working yesterday, what happened?"
"Which step is producing wrong output?"
"I can't reproduce the bug from production"

Your logs say the agent ran. They don't say what it decided or why.

Install

pip install work-ledger

30-Second Example

from work_ledger import WorkLedger

ledger = WorkLedger(store="./runs")

# Record a run
with ledger.run(name="my-agent") as run:
    run.record_input({"query": "What's the weather?"})
    
    with run.step("llm-call", kind="model") as step:
        response = "It's sunny, 72°F"  # Your LLM call here
        step.record_output({"response": response})
    
    run.record_output({"answer": response})

# See what was recorded
print(ledger.list_runs()[0].to_dict())

See the Diff

work-ledger diff ./runs <run1> <run2>

Comparing runs:
  Expected: abc123... (my-agent)
  Actual:   def456... (my-agent)

Similarity: 58.3%

Output changes:
  ~ answer: "It's sunny..." → "It's cloudy..."

Step changes:
  + retrieve-weather [retrieval]

Metric changes:
  total_tokens: 150 → 460

Now you know what broke.

One-Line Integrations

from work_ledger import WorkLedger, wrap_agent, wrap_graph, wrap_chain

ledger = WorkLedger(store="./runs")

# PydanticAI
wrapped = wrap_agent(my_agent, ledger)
result = wrapped.run_sync("Hello!")

# LangGraph  
wrapped = wrap_graph(my_graph, ledger)
result = wrapped.invoke({"messages": [...]})

# LangChain
wrapped = wrap_chain(my_chain, ledger)
result = wrapped.invoke({"question": "..."})

Also supports: CrewAI, LlamaIndex, OpenAI SDK, Anthropic SDK. See docs/integrations.md for details.

Try the Samples

git clone https://github.com/metawake/work-ledger.git
cd work-ledger && pip install -e .

python samples/03_detect_regression.py  # See a diff in action

| Your Problem | Sample | |--------------|--------| | "I want to see what my agent did" | 01_basic_recording.py | | "Something changed, what?" | 03_detect_regression.py | | "I use PydanticAI/LangGraph/CrewAI" | 05-07_*.py |

Replay Without API Calls

Record once, replay forever — no API key needed:

# Record (makes real API call)
wrapped = wrap_openai(client, ledger)
response = wrapped.chat.completions.create(...)
run_id = ledger.list_runs()[0].run_id

# Replay (returns saved response, no API call)
wrapped = wrap_openai(client, ledger, replay_from=run_id)
response = wrapped.chat.completions.create(...)  # Instant, free

Perfect for: CI/CD testing, debugging, offline development.

CLI

work-ledger list ./runs              # List all runs
work-ledger show ./runs <run_id>     # Show run details
work-ledger diff ./runs <id1> <id2>  # Compare two runs
work-ledger replay ./runs <run_id>   # Show replay info
work-ledger list ./runs --json       # JSON output

Storage

# Local (default)
ledger = WorkLedger(store="./runs")

# SQLite
ledger = WorkLedger(store=SQLiteStore("./runs.db"))

# PostgreSQL, Redis, MongoDB, S3, GCS also supported

See docs/storage.md for all 8 backends.

Testing

Work Ledger includes decorators for regression testing:

from work_ledger.testing import recorded, golden, RunDiff

@recorded("fixtures/baseline.json")
def test_agent():
    result = agent.run("test")
    assert "response" in result

# Compare runs programmatically
diff = RunDiff(old_run, new_run)
assert diff.similarity > 0.95

See docs/testing.md for the full testing API.

What It Does

| Action | What It Does | |--------|--------------| | Record | Capture every step, input, output, and decision | | Replay | Re-run using saved fixtures — no API calls needed | | Diff | See exactly what changed between two runs | | Debug | Trace causal chains — what triggered what |

What It Doesn't Do

❌ SaaS dashboard
❌ Replace observability tools
❌ Require a specific agent framework

Work Ledger is small and composable.

Tested With

| Integration | Tested Version | Notes | |-------------|----------------|-------| | OpenAI SDK | 1.50+ | v1 API, stable | | Anthropic SDK | 0.40+ | Pre-1.0 but stable | | PydanticAI | 0.0.20+ | Rapidly evolving | | LangChain | 0.2+ | Core + chains | | LangGraph | 0.2+ | Graph execution | | CrewAI | 0.70+ | Multi-agent | | LlamaIndex | 0.10+ | RAG pipelines |

Using an older version? It may still work — we use duck typing. Open an issue if you hit problems.

Documentation

Integrations — Framework wrappers
Storage — 8 storage backends
Testing — Regression testing
Data Model — Run/Step structure

Contributing

See CONTRIBUTING.md for guidelines.

License

MIT — see LICENSE.

Work Ledger Because agent runs deserve to be understood, not just logged.

Contract & API

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

MissingGITHUB OPENCLEW

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

missing

Auth

None

Streaming

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://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/snapshot"

curl -s "https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/contract"

curl -s "https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/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_REPOSactivepieces

Rank

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

Traction

No public download signal

Freshness

Updated 2d ago

OPENCLAW

GITHUB_REPOScherry-studio

Rank

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW

GITHUB_REPOSAionUi

Rank

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!

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW

GITHUB_REPOSCopilotKit

Rank

The Frontend for Agents & Generative UI. React + Angular

Traction

No public download signal

Freshness

Updated 23d ago

OPENCLAW

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://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-17T02:15:05.502Z"
    }
  },
  "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": "Metawake",
    "href": "https://github.com/metawake/work-ledger",
    "sourceUrl": "https://github.com/metawake/work-ledger",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T06:04:35.623Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T06:04:35.623Z",
    "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://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/crewai-metawake-work-ledger/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · 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
  }
]

work-ledger answer-first brief

Executive Summary

Evidence Ledger

Release & Crawl Timeline

Artifacts Archive

Docs & README

Work Ledger

The Problem

Install

30-Second Example

See the Diff

One-Line Integrations

Try the Samples

Replay Without API Calls

CLI

Storage

Testing

What It Does

What It Doesn't Do

Tested With

Documentation

See Also

Contributing

License

Contract & API

Reliability & Benchmarks

Media & Demo

Related Agents