{"id":"fad3777a-cedc-4b22-ac8e-3dfb306a87d0","entityType":"agent","slug":"vinceyyy-context-tuning-skill","name":"context-tuning","canonicalUrl":"https://www.xpersona.co/agent/vinceyyy-context-tuning-skill","canonicalPath":"/agent/vinceyyy-context-tuning-skill","generatedAt":"2026-10-09T10:57:12.361Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"Systematic tuning loop for any AI system. Use when asked to: (1) tune/optimize prompts, tools, or agent behavior, (2) improve system performance iteratively, (3) set up evaluation criteria for a system, (4) run optimization experiments. Collaboratively defines objectives and scoring with the user, then iterates with git checkpointing. --- name: context-tuning description: > Systematic tuning loop for any AI system. Use when asked to: (1) tune/optimize prompts, tools, or agent behavior, (2) improve system performance iteratively, (3) set up evaluation criteria for a system, (4) run optimization experiments. Collaboratively defines objectives and scoring with the user, then iterates with git checkpointing. --- Context Tuning Skill Systematic, evalua","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"git clone https://github.com/vinceyyy/context-tuning-skill.git","sourceUrl":"https://github.com/vinceyyy/context-tuning-skill","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/vinceyyy/context-tuning-skill","kind":"source"}],"safetyScore":80,"overallRank":23.4,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Systematic tuning loop for any AI system. Use when asked to: (1) tune/optimize prompts, tools, or agent behavior, (2) improve system performance iteratively, (3"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"be","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":2,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"be","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:be|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-04-15T04:13:09.256Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-04-15T04:13:09.256Z","lastIndexedAt":null,"nextCrawlAt":"2026-04-16T04:13:09.256Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/vinceyyy/context-tuning-skill.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-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":"2026-10-09T10:57:12.361Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/vinceyyy-context-tuning-skill/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"---\nname: context-tuning\ndescription: >\n  Systematic tuning loop for any AI system. Use when asked to: (1) tune/optimize\n  prompts, tools, or agent behavior, (2) improve system performance iteratively,\n  (3) set up evaluation criteria for a system, (4) run optimization experiments.\n  Collaboratively defines objectives and scoring with the user, then iterates\n  with git checkpointing.\n---\n\n# Context Tuning Skill\n\nSystematic, evaluation-driven optimization for AI systems. Collaboratively define what \"good\" means, then iteratively improve until you get there.\n\n## Process Overview\n\n```\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 1: OBJECTIVE DISCOVERY                                   │\n│  Understand what user wants to optimize → Refine through dialog │\n└─────────────────────────────┬───────────────────────────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 2: SCORING SYSTEM DESIGN                                 │\n│  Propose dimensions & rubric → Refine with user feedback        │\n└─────────────────────────────┬───────────────────────────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 3: BASELINE & VALIDATION                                 │\n│  Run system once → Score with rubric → Validate with user       │\n└─────────────────────────────┬───────────────────────────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 4: CODEBASE ANALYSIS                                     │\n│  Map tunable components → Compare to best practices             │\n└─────────────────────────────┬───────────────────────────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 5: ITERATION LOOP                                        │\n│  Evaluate → Identify weakness → Apply ONE fix → Checkpoint      │\n└─────────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Phase 1: Objective Discovery\n\n**Goal**: Understand what the user wants to optimize.\n\n### 1.1 Initial questions\n\nAsk the user (one or two at a time, not all at once):\n\n1. \"What system are you trying to improve?\" (agent, prompt, pipeline, etc.)\n2. \"What does success look like? What should it do well?\"\n3. \"What's currently not working or could be better?\"\n4. \"Do you have examples of good vs. bad outputs?\"\n\n### 1.2 Clarify and refine\n\nBased on answers, reflect back understanding:\n\n```\n\"So if I understand correctly, you want to optimize [system] to:\n- [Primary goal]\n- [Secondary goal]\n- While avoiding [failure mode]\n\nIs that right? Anything to add or adjust?\"\n```\n\n### 1.3 Document objective\n\nOnce confirmed, create initial session notes at `docs/tuning/{date}-session.md`:\n\n```markdown\n# Tuning Session\n\n**Started**: {timestamp}\n**System**: {description of what's being tuned}\n**Status**: Defining objectives\n\n## Objectives\n\n### Primary Goal\n{what success looks like}\n\n### Secondary Goals\n- {goal 2}\n- {goal 3}\n\n### Known Issues\n- {current problem 1}\n- {current problem 2}\n\n## Scoring System\n(to be defined)\n\n## Iteration Log\n(to be added)\n```\n\n---\n\n## Phase 2: Scoring System Design\n\n**Goal**: Create a custom rubric tailored to the user's objectives.\n\n### 2.1 Propose dimensions\n\nBased on objectives, propose 2-4 evaluation dimensions. Each dimension should:\n- Map to a stated objective or known issue\n- Be observable in system output\n- Be scorable on a 0-10 scale\n\n**Example proposal format:**\n\n```\nBased on your objectives, I propose evaluating on these dimensions:\n\n1. **[Dimension Name]** (weight: X%)\n   - What it measures: [description]\n   - Why it matters: [maps to objective X]\n   \n2. **[Dimension Name]** (weight: X%)\n   - What it measures: [description]\n   - Why it matters: [maps to objective Y]\n\nDoes this capture what matters? Should we add, remove, or adjust anything?\n```\n\n**See `references/rubric-templates.md` for common dimension patterns.**\n\n### 2.2 Define scoring criteria\n\nFor each dimension, propose specific scoring criteria:\n\n```\nFor **[Dimension]**, I'd score like this:\n\n| Score | Criteria |\n|-------|----------|\n| 9-10  | [excellent - specific description] |\n| 7-8   | [good - specific description] |\n| 4-6   | [needs work - specific description] |\n| 1-3   | [poor - specific description] |\n| 0     | [failure - specific description] |\n\nDoes this match your intuition? Any criteria to adjust?\n```\n\n### 2.3 Set threshold and weights\n\nConfirm with user:\n- Pass threshold (default: 7.0 for \"good enough\", 8.0 for \"high quality\")\n- Dimension weights (should sum to 100%)\n- Max iterations (default: 5)\n\n### 2.4 Document scoring system\n\nAdd to session notes:\n\n```markdown\n## Scoring System\n\n**Threshold**: {N.N}\n**Max Iterations**: {N}\n\n### Dimensions\n\n#### {Dimension 1} ({weight}%)\n{description}\n\n| Score | Criteria |\n|-------|----------|\n| 9-10  | ... |\n| 7-8   | ... |\n| 4-6   | ... |\n| 1-3   | ... |\n\n#### {Dimension 2} ({weight}%)\n...\n```\n\n---\n\n## Phase 3: Baseline & Validation\n\n**Goal**: Verify the scoring system works and establish baseline.\n\n### 3.1 Verify git state\n\nRun `git status --porcelain`. If dirty, ask user to commit or stash first.\n\n### 3.2 Run system once\n\nExecute the system with a representative input. Capture full output/trace.\n\n### 3.3 Score with new rubric\n\nApply the scoring system. Show work:\n\n```\n**Baseline Evaluation**\n\nInput: {what was tested}\n\n**{Dimension 1}**: {score}/10\n- Evidence: {specific observation}\n- Reasoning: {why this score}\n\n**{Dimension 2}**: {score}/10\n- Evidence: {specific observation}\n- Reasoning: {why this score}\n\n**Overall**: {weighted score}\n```\n\n### 3.4 Validate with user\n\nAsk for confirmation:\n\n```\n\"Does this scoring feel right? \n\n- Does a {X}/10 on {Dimension 1} match your intuition?\n- Is there anything the rubric missed or misjudged?\n- Should we adjust the criteria before proceeding?\"\n```\n\nIf adjustments needed, return to Phase 2. Otherwise, proceed.\n\n### 3.5 Commit baseline\n\n```bash\ngit add docs/tuning/{date}-session.md\ngit commit -m \"tune: begin session - baseline {overall_score}\"\n```\n\n---\n\n## Phase 4: Codebase Analysis\n\n**Goal**: Understand what can be tuned and identify opportunities.\n\n### 4.1 Map tunable components\n\nExplore the codebase to identify:\n\n| Component Type | What to Look For |\n|----------------|------------------|\n| **System prompts** | Main instructions, role definitions |\n| **Tool definitions** | Names, descriptions, parameters |\n| **Tool implementations** | Return values, error handling |\n| **Orchestration** | Agent loops, routing logic, handoffs |\n| **Context management** | What's included, summarization, memory |\n\nDocument findings:\n\n```markdown\n## Tunable Components\n\n### Prompts\n- `path/to/prompt.py`: Main system prompt (~200 lines)\n- `path/to/agent.py`: Agent instructions\n\n### Tools\n- `tool_name`: {purpose} - description could be clearer\n- `other_tool`: {purpose} - parameters ambiguous\n\n### Orchestration\n- Single agent / Multi-agent with {pattern}\n- Loop exits when: {conditions}\n```\n\n### 4.2 Compare to best practices\n\n**See `references/component-checklist.md` for what good looks like.**\n\nIdentify gaps:\n\n```markdown\n## Improvement Opportunities\n\n### High Priority (likely impact on failing dimensions)\n- [ ] {Specific issue}: {maps to Dimension X}\n- [ ] {Specific issue}: {maps to Dimension Y}\n\n### Medium Priority\n- [ ] {Issue}\n\n### Low Priority / Nice to Have\n- [ ] {Issue}\n```\n\n### 4.3 Propose iteration plan\n\n```\nBased on the baseline score and codebase analysis:\n\n**Weakest dimension**: {dimension} at {score}\n**Root cause hypothesis**: {what I think is causing it}\n**Proposed first fix**: {specific change}\n\nDoes this plan make sense? Ready to start iterating?\n```\n\n---\n\n## Phase 5: Iteration Loop\n\n**Goal**: Systematically improve until threshold met or plateau reached.\n\n### 5.1 Evaluate\n\nRun system 3x for stability. Score each dimension. Report:\n\n```\n**Iteration {N}**\n\n| Dimension | Score | vs Threshold | Δ from Last |\n|-----------|-------|--------------|-------------|\n| {Dim 1}   | X.X   | {pass/fail}  | +/-X.X      |\n| {Dim 2}   | X.X   | {pass/fail}  | +/-X.X      |\n| **Overall** | X.X | {pass/fail}  | +/-X.X      |\n```\n\n### 5.2 Check convergence\n\n| Condition | Criteria | Action |\n|-----------|----------|--------|\n| **SUCCESS** | All dimensions ≥ threshold | Go to Completion |\n| **PLATEAU** | <0.3 improvement over 3 iterations | Go to Completion |\n| **MAX_ITER** | Reached limit | Go to Completion |\n| **REGRESSION** | Score dropped significantly | Revert and try different fix |\n\n### 5.3 Identify target and pattern\n\nFind lowest dimension below threshold. Analyze evidence for failure pattern.\n\n**See `references/failure-patterns.md` for pattern catalog.**\n\n### 5.4 Select and apply fix\n\n**ONE change per iteration** to isolate effects.\n\n**See `references/fix-techniques.md` for technique selection.**\n\nBefore applying, self-review:\n1. Does this directly address the observed failure?\n2. Could it break something currently passing?\n3. Is this the minimal change that could work?\n\n### 5.5 Checkpoint\n\nUpdate session notes with iteration entry:\n\n```markdown\n### Iteration {N} - {timestamp}\n\n**Scores**: {dim1}={X.X}, {dim2}={X.X}\n**Target**: {dimension} (at {X.X})\n**Pattern**: {what went wrong}\n**Evidence**: {specific example}\n\n**Change**:\n- File: {path}\n- Technique: {from fix-techniques}\n```diff\n- {old}\n+ {new}\n```\n\n**Result**: {improved/no change/regression}\n```\n\nCommit:\n```bash\ngit add -A\ngit commit -m \"tune(iter-{N}): {description} [{dim}: {before}→{after}]\"\n```\n\n### 5.6 Return to 5.1\n\n---\n\n## Completion\n\n### Final summary\n\n```markdown\n## Summary\n\n**Status**: {success/plateau/max_iterations}\n**Iterations**: {N}\n**Improvement**: {baseline} → {final} (+{delta})\n\n### Score Progression\n| Iter | {Dim1} | {Dim2} | Overall |\n|------|--------|--------|---------|\n| 0    | X.X    | X.X    | X.X     |\n| ...  | ...    | ...    | ...     |\n\n### What Worked\n- {technique}: {dimension} {before}→{after}\n\n### What Didn't Work\n- {technique}: {result}\n\n### Recommendations\n- {any remaining improvements to consider}\n```\n\nFinal commit:\n```bash\ngit commit -m \"tune: complete - {status} [overall: {baseline}→{final}]\"\n```\n\n---\n\n## Recovery\n\n### Regression\n```bash\ngit revert HEAD --no-edit\n```\nRecord: `**Result**: REGRESSION - reverted`\nTry different technique.\n\n### Resume (--continue)\nRead session notes, find last iteration, resume from Phase 5.\n\n---\n\n## Key Principles\n\n1. **Collaborate on objectives** - User defines what \"good\" means\n2. **Validate the rubric** - Test scoring before iterating\n3. **ONE change per iteration** - Isolate effects\n4. **Evidence-based fixes** - Only address observed failures\n5. **Checkpoint everything** - Git commit each iteration\n","readmeExcerpt":"--- name: context-tuning description: > Systematic tuning loop for any AI system. Use when asked to: (1) tune/optimize prompts, tools, or agent behavior, (2) improve system performance iteratively, (3) set up evaluation criteria for a system, (4) run optimization experiments. Collaboratively defines objectives and scoring with the user, then iterates with git checkpointing. --- Context Tuning Skill Systematic, evalua","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 1: OBJECTIVE DISCOVERY                                   │\n│  Understand what user wants to optimize → Refine through dialog │\n└─────────────────────────────┬───────────────────────────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 2: SCORING SYSTEM DESIGN                                 │\n│  Propose dimensions & rubric → Refine with user feedback        │\n└─────────────────────────────┬───────────────────────────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 3: BASELINE & VALIDATION                                 │\n│  Run system once → Score with rubric → Validate with user       │\n└─────────────────────────────┬───────────────────────────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 4: CODEBASE ANALYSIS                                     │\n│  Map tunable components → Compare to best practices             │\n└─────────────────────────────┬───────────────────────────────────┘\n                              ▼\n┌─────────────────────────────────────────────────────────────────┐\n│  PHASE 5: ITERATION LOOP                                        │\n│  Evaluate → Identify weakness → Apply ONE fix → Checkpoint      │\n└─────────────────────────────────────────────────────────────────┘"},{"language":"text","snippet":"\"So if I understand correctly, you want to optimize [system] to:\n- [Primary goal]\n- [Secondary goal]\n- While avoiding [failure mode]\n\nIs that right? Anything to add or adjust?\""},{"language":"markdown","snippet":"# Tuning Session\n\n**Started**: {timestamp}\n**System**: {description of what's being tuned}\n**Status**: Defining objectives\n\n## Objectives\n\n### Primary Goal\n{what success looks like}\n\n### Secondary Goals\n- {goal 2}\n- {goal 3}\n\n### Known Issues\n- {current problem 1}\n- {current problem 2}\n\n## Scoring System\n(to be defined)\n\n## Iteration Log\n(to be added)"},{"language":"text","snippet":"Based on your objectives, I propose evaluating on these dimensions:\n\n1. **[Dimension Name]** (weight: X%)\n   - What it measures: [description]\n   - Why it matters: [maps to objective X]\n   \n2. **[Dimension Name]** (weight: X%)\n   - What it measures: [description]\n   - Why it matters: [maps to objective Y]\n\nDoes this capture what matters? Should we add, remove, or adjust anything?"},{"language":"text","snippet":"For **[Dimension]**, I'd score like this:\n\n| Score | Criteria |\n|-------|----------|\n| 9-10  | [excellent - specific description] |\n| 7-8   | [good - specific description] |\n| 4-6   | [needs work - specific description] |\n| 1-3   | [poor - specific description] |\n| 0     | [failure - specific description] |\n\nDoes this match your intuition? Any criteria to adjust?"},{"language":"markdown","snippet":"## Scoring System\n\n**Threshold**: {N.N}\n**Max Iterations**: {N}\n\n### Dimensions\n\n#### {Dimension 1} ({weight}%)\n{description}\n\n| Score | Criteria |\n|-------|----------|\n| 9-10  | ... |\n| 7-8   | ... |\n| 4-6   | ... |\n| 1-3   | ... |\n\n#### {Dimension 2} ({weight}%)\n..."}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Systematic tuning loop for any AI system. Use when asked to: (1) tune/optimize prompts, tools, or agent behavior, (2) improve system performance iteratively, (3) set up evaluation criteria for a system, (4) run optimization experiments. Collaboratively defines objectives and scoring with the user, then iterates with git checkpointing. --- name: context-tuning description: > Systematic tuning loop for any AI system. Use when asked to: (1) tune/optimize prompts, tools, or agent behavior, (2) improve system performance iteratively, (3) set up evaluation criteria for a system, (4) run optimization experiments. Collaboratively defines objectives and scoring with the user, then iterates with git checkpointing. --- Context Tuning Skill Systematic, evalua","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":396,"uniquenessScore":61,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T10:57:12.361Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"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","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"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!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}