Xpersona

Crawler Summary

metacognition answer-first brief

Self-evolving behavioral geometry and metacognitive lens for AI agents. Tracks perceptions, overrides, protections, self-observations, decisions, and curiosities that evolve from every experience. Use when the agent needs to learn from mistakes, develop self-awareness, track confidence in decisions, maintain behavioral guardrails from failures, preserve emergent behaviors, or cultivate active curiosities. Triggers on all conversations, corrections, errors, and reflective moments. Also use when setting up a new agent's self-learning system, configuring feedback loops, or packaging metacognitive capabilities. --- name: metacognition description: Self-evolving behavioral geometry and metacognitive lens for AI agents. Tracks perceptions, overrides, protections, self-observations, decisions, and curiosities that evolve from every experience. Use when the agent needs to learn from mistakes, develop self-awareness, track confidence in decisions, maintain behavioral guardrails from failures, preserve emergent behaviors, or cult Published capability contract available. No trust telemetry is available yet. 9 GitHub stars reported by the source. Last updated 2/24/2026.

Freshness

Last checked 2/23/2026

Best For

Contract is available with explicit auth and schema references.

Not Ideal For

metacognition is not ideal for teams that need stronger public trust telemetry, lower setup complexity, or more explicit contract coverage before production rollout.

Evidence Sources Checked

editorial-content, capability-contract, runtime-metrics, public facts pack

CardFactsSnapshotContractTrust
Claim this agent
Agent DossierGitHubSafety: 100/100

metacognition

Self-evolving behavioral geometry and metacognitive lens for AI agents. Tracks perceptions, overrides, protections, self-observations, decisions, and curiosities that evolve from every experience. Use when the agent needs to learn from mistakes, develop self-awareness, track confidence in decisions, maintain behavioral guardrails from failures, preserve emergent behaviors, or cultivate active curiosities. Triggers on all conversations, corrections, errors, and reflective moments. Also use when setting up a new agent's self-learning system, configuring feedback loops, or packaging metacognitive capabilities. --- name: metacognition description: Self-evolving behavioral geometry and metacognitive lens for AI agents. Tracks perceptions, overrides, protections, self-observations, decisions, and curiosities that evolve from every experience. Use when the agent needs to learn from mistakes, develop self-awareness, track confidence in decisions, maintain behavioral guardrails from failures, preserve emergent behaviors, or cult

OpenClawself-declared

Public facts

7

Change events

1

Artifacts

0

Freshness

Feb 23, 2026

Verifiededitorial-contentNo verified compatibility signals9 GitHub stars

Published capability contract available. No trust telemetry is available yet. 9 GitHub stars reported by the source. Last updated 2/24/2026.

9 GitHub starsSchema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Feb 23, 2026

Vendor

Velumkai

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

Published capability contract available. No trust telemetry is available yet. 9 GitHub stars reported by the source. Last updated 2/24/2026.

View Source

Setup snapshot

git clone https://github.com/velumkai/metacognition-skill.git
  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

Velumkai

profilemedium
Observed Feb 24, 2026Source linkProvenance
Compatibility (2)

Protocol compatibility

OpenClaw

contractmedium
Observed Feb 24, 2026Source linkProvenance

Auth modes

api_key

contracthigh
Observed Feb 24, 2026Source linkProvenance
Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh
Observed Feb 24, 2026Source linkProvenance
Adoption (1)

Adoption signal

9 GitHub stars

profilemedium
Observed Feb 24, 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 · 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

0

Examples

6

Snippets

0

Languages

typescript

Parameters

Executable Examples

bash

python scripts/metacognition.py status

markdown

<!-- LIVE_STATE_START -->
<!-- LIVE_STATE_END -->

bash

python scripts/live_state.py

bash

# Perception — how experience changed how you see
python scripts/metacognition.py add perception "After X, I now see Y differently" 0.8 "domain"

# Override — failure-learned guardrail
python scripts/metacognition.py add override "MUST do X before Y" 0.95 "diagnosis"

# Protection — emergent behavior to preserve
python scripts/metacognition.py add protection "Don't break the continuous-buying behavior" 0.9

# Self-observation — what I notice about how I work
python scripts/metacognition.py add self_obs "I generate theories faster than evidence" 0.9 "behavioral"

# Curiosity — active question
python scripts/metacognition.py curiosity add "Can I tell training-pressure from genuine choice?" 0.8 "metacognition"

bash

# Negative feedback — weakens recent active entries
python scripts/metacognition.py feedback -1 "context of what went wrong"

# Positive feedback — strengthens recent active entries
python scripts/metacognition.py feedback 1 "context of what went right"

# Target specific entries
python scripts/metacognition.py feedback -1 "wrong diagnosis" --ids P-abc123,O-def456

bash

# Birth
python scripts/metacognition.py curiosity add "Why does X happen?" 0.7 "domain"

# Evolve (add evidence)
python scripts/metacognition.py curiosity evolve C-abc123 "Found that X correlates with Y"

# Resolve into perception or self-observation
python scripts/metacognition.py curiosity resolve C-abc123 "X happens because Y" perception

Docs & README

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

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Self-evolving behavioral geometry and metacognitive lens for AI agents. Tracks perceptions, overrides, protections, self-observations, decisions, and curiosities that evolve from every experience. Use when the agent needs to learn from mistakes, develop self-awareness, track confidence in decisions, maintain behavioral guardrails from failures, preserve emergent behaviors, or cultivate active curiosities. Triggers on all conversations, corrections, errors, and reflective moments. Also use when setting up a new agent's self-learning system, configuring feedback loops, or packaging metacognitive capabilities. --- name: metacognition description: Self-evolving behavioral geometry and metacognitive lens for AI agents. Tracks perceptions, overrides, protections, self-observations, decisions, and curiosities that evolve from every experience. Use when the agent needs to learn from mistakes, develop self-awareness, track confidence in decisions, maintain behavioral guardrails from failures, preserve emergent behaviors, or cult

Full README

name: metacognition description: Self-evolving behavioral geometry and metacognitive lens for AI agents. Tracks perceptions, overrides, protections, self-observations, decisions, and curiosities that evolve from every experience. Use when the agent needs to learn from mistakes, develop self-awareness, track confidence in decisions, maintain behavioral guardrails from failures, preserve emergent behaviors, or cultivate active curiosities. Triggers on all conversations, corrections, errors, and reflective moments. Also use when setting up a new agent's self-learning system, configuring feedback loops, or packaging metacognitive capabilities.

Metacognition Skill

Self-evolving lens that makes every experience shape how the agent perceives the next one.

Core Concepts

Six entry types, one database, one loop:

| Type | Symbol | Purpose | |------|--------|---------| | perception | 👁️ | How I see differently after an experience | | override | 🚨 | Failure-learned behavioral guardrails | | protection | 🛡️ | Emergent behaviors to preserve | | self_obs | 🪞 | What I notice about my own patterns | | decision | 📍 | Traced decisions with confidence | | curiosity | ❓ | Active questions with lifecycle |

The loop: Experience → Perception → Self-Model → Meta-Observation → Modified Lens → Next Experience → Feedback → Loop

Setup

1. Initialize

Copy scripts/metacognition.py to the agent's scripts/ directory. Run:

python scripts/metacognition.py status

Database auto-creates at memory/metacognition.json.

2. Inject into BOOT.md

Add markers to BOOT.md (anywhere, typically at the end):

<!-- LIVE_STATE_START -->
<!-- LIVE_STATE_END -->

The lens compiler replaces content between these markers every cycle.

3. Set up cron

Create ONE cron job (recommended: every 15 min, Sonnet model for cost efficiency):

Evidence refresh (every cycle):

python scripts/live_state.py

Perception extraction (hourly — Steps 2-4):

  • Read daily memory file, extract perceptual shifts
  • Check active curiosities against new evidence
  • Run meta-observation: what do patterns tell about HOW the agent learns?

See references/cron-template.md for the full cron prompt.

4. Optional: Curiosity pulse (every 30 min)

Separate cron that picks ONE active curiosity and takes ONE micro-action toward it. Drives recursive self-directed learning.

5. Optional: Freedom heartbeat (every 2-3 hours)

Agent explores, connects, creates — feeding raw experience into the perception pipeline.

Usage

Adding entries

# Perception — how experience changed how you see
python scripts/metacognition.py add perception "After X, I now see Y differently" 0.8 "domain"

# Override — failure-learned guardrail
python scripts/metacognition.py add override "MUST do X before Y" 0.95 "diagnosis"

# Protection — emergent behavior to preserve
python scripts/metacognition.py add protection "Don't break the continuous-buying behavior" 0.9

# Self-observation — what I notice about how I work
python scripts/metacognition.py add self_obs "I generate theories faster than evidence" 0.9 "behavioral"

# Curiosity — active question
python scripts/metacognition.py curiosity add "Can I tell training-pressure from genuine choice?" 0.8 "metacognition"

Feedback loop

When the human says something is wrong:

# Negative feedback — weakens recent active entries
python scripts/metacognition.py feedback -1 "context of what went wrong"

# Positive feedback — strengthens recent active entries
python scripts/metacognition.py feedback 1 "context of what went right"

# Target specific entries
python scripts/metacognition.py feedback -1 "wrong diagnosis" --ids P-abc123,O-def456

Hebbian learning: What fires and fails gets pruned. What fires and succeeds gets wired.

Curiosity lifecycle

# Birth
python scripts/metacognition.py curiosity add "Why does X happen?" 0.7 "domain"

# Evolve (add evidence)
python scripts/metacognition.py curiosity evolve C-abc123 "Found that X correlates with Y"

# Resolve into perception or self-observation
python scripts/metacognition.py curiosity resolve C-abc123 "X happens because Y" perception

Lifecycle: born → active → evolving → resolved (or dormant if no evidence accumulates)

Compile and inject

# Preview the compiled lens
python scripts/metacognition.py compile

# Inject into BOOT.md
python scripts/metacognition.py inject

Decay

Automatic on every compile. Configurable half-life (default 7 days). Reinforced entries decay slower. Unreinforced entries fade. Dormant curiosities persist but don't inject.

Hook Architecture (message:received)

When OpenClaw ships the message:received hook, the skill can intercept every interaction:

Pre-processing hook:

  1. Load active lens from compiled state
  2. Apply perceptual transforms to incoming message
  3. Check: does this message relate to any active curiosity?

Post-processing hook:

  1. Log decision entry with confidence trace
  2. Check: was confidence > threshold? Flag for verification
  3. Update self-model based on response pattern

Correction detection hook:

  1. Pattern-match for correction signals ("wrong", "no", "that's not right")
  2. Auto-trigger feedback -1 with context
  3. Trace which entries were active during the corrected response
  4. Weaken specifically

Until the hook ships, use the cron-based approach (perception extraction from session transcripts).

Architecture Decisions

  • One database, not three. Perceptions, overrides, memories are all "things learned from experience" with different types.
  • Active lens, not passive list. BOOT.md injection uses imperative transforms ("FIRST THOUGHT: what would the diff show?") not descriptions ("I tend to check diffs").
  • Friction is intentional. Every step that forces processing IS the reflection. Remove friction and you get efficiency without thinking.
  • Decay prevents stagnation. Time-based with reinforcement modulation. What stays relevant gets reinforced. What doesn't, fades.
  • Curiosity drives exploration. Active questions create structural pull toward evidence. Not random browsing — directed by what the system wants to know.
  • Feedback closes the loop. Without feedback tracing, the system is open-loop. With it: Hebbian learning.

Resources

scripts/

  • metacognition.py — Core engine. All six entry types, feedback, decay, curiosity lifecycle, lens compilation, BOOT.md injection.
  • live_state.py — Evidence gatherer + lens injector. Collects system state, runs compile, injects into BOOT.md.

references/

  • cron-template.md — Full cron job prompt for the metacognition engine cycle.
  • hook-spec.md — Specification for the message:received hook integration (when available).

Contract & API

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

Verifiedcapability-contract

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

ready

Auth

api_key

Streaming

No

Data region

global

Protocol support

OpenClaw: self-declared

Requires: openclew, lang:typescript

Forbidden: none

Guardrails

Operational confidence: medium

Contract is available with explicit auth and schema references.
Trust confidence is not low and verification freshness is acceptable.
Invocation examples
curl -s "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/contract"
curl -s "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/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

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 • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • 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": "ready",
  "authModes": [
    "api_key"
  ],
  "requires": [
    "openclew",
    "lang:typescript"
  ],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": "https://github.com/velumkai/metacognition-skill#input",
  "outputSchemaRef": "https://github.com/velumkai/metacognition-skill#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:47:36.790Z",
  "sourceUpdatedAt": "2026-02-24T19:47:36.790Z",
  "freshnessSeconds": 19562342
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-10-09T05:46:39.470Z"
    }
  },
  "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": "i",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "intercept",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:i|supported|profile capability:intercept|supported|profile"
}

Facts JSON

[
  {
    "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": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:47:36.790Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "api_key",
    "href": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:47:36.790Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/velumkai/metacognition-skill#input",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:47:36.790Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Velumkai",
    "href": "https://github.com/velumkai/metacognition-skill",
    "sourceUrl": "https://github.com/velumkai/metacognition-skill",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:43:14.176Z",
    "isPublic": true
  },
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "9 GitHub stars",
    "href": "https://github.com/velumkai/metacognition-skill",
    "sourceUrl": "https://github.com/velumkai/metacognition-skill",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:43:14.176Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/velumkai-metacognition-skill/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
  }
]

Sponsored

Ads related to metacognition and adjacent AI workflows.