{"id":"78c3ad1a-6e04-4441-a96a-4609ef564e6b","entityType":"agent","slug":"crewai-lukatcheishvili-claimsops-agent","name":"claimsops-agent","canonicalUrl":"https://www.xpersona.co/agent/crewai-lukatcheishvili-claimsops-agent","canonicalPath":"/agent/crewai-lukatcheishvili-claimsops-agent","generatedAt":"2026-10-10T02:03:03.114Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T18:14:05.230Z","emptyReason":null},"description":"Agentic AI MVP for insurance claims operations. A multi-agent workflow intakes a claim, verifies coverage, inspects evidence, scores operational risk, recommends the next action and drafts communications — while keeping final decisions human-gated. Built as both a Next.js web app and a Streamlit + CrewAI implementation. ClaimsOps Agent **Live Demo:** $1 Agentic AI MVP for **Insurance Claims Operations**. ClaimsOps Agent demonstrates how a multi-agent workflow can intake a claim, verify coverage, inspect evidence, score operational risk, recommend the next action, draft communications, and keep final insurance decisions human-gated. The repo contains two working interfaces: - **Vercel / Next.js app**: polished web MVP for deployment","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/lukatcheishvili/claimsops-agent","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/lukatcheishvili/claimsops-agent","kind":"source"}],"safetyScore":66,"overallRank":18.8,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Agentic AI MVP for insurance claims operations. A multi-agent workflow intakes a claim, verifies coverage, inspects evidence, scores operational risk, recommend"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T18:14:05.230Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"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"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T18:14:05.230Z","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":"2026-10-09T18:14:05.224Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T18:14:05.230Z","lastCrawledAt":"2026-10-09T18:14:05.224Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T18:14:05.224Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"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/crewai-lukatcheishvili-claimsops-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-10T02:03:03.114Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-lukatcheishvili-claimsops-agent/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 REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T18:14:05.230Z","emptyReason":null},"readme":"# ClaimsOps Agent\n\n**Live Demo:** [Open the Vercel MVP](https://claimsops-agent-git-main-lukatcheishvilis-projects.vercel.app/)\n\nAgentic AI MVP for **Insurance Claims Operations**. ClaimsOps Agent demonstrates how a multi-agent workflow can intake a claim, verify coverage, inspect evidence, score operational risk, recommend the next action, draft communications, and keep final insurance decisions human-gated.\n\nThe repo contains two working interfaces:\n\n- **Vercel / Next.js app**: polished web MVP for deployment and presentation.\n- **Streamlit app**: Python MVP with optional CrewAI + Vertex AI live mode.\n\n## What Is New\n\n- **Resizable Agent Chat Rail**: users can ask the ClaimsOps agent about risk, evidence, coverage, routing, Vertex status, audit history, and architecture from a dedicated right-side chat rail. The rail can be toggled on/off or dragged wider from its left edge.\n- **Guided Demo Mode**: a step-by-step walkthrough for class presentation.\n- **Evidence Upload Simulation**: missing evidence can be added from the intake form to show how readiness changes.\n- **Downloadable Claim Review**: exports an HTML review package with summary, risk drivers, trace, and approval log.\n- **Human Approval Action Log**: approval, evidence request, and escalation actions are recorded.\n- **Manager View**: shows highest-value operational signals: manual queue, evidence blockers, high-risk claims, urgent SLAs, owner load, and recommended management actions.\n- **Vertex Runtime Status**: makes live-mode readiness visible without hiding deterministic fallback behavior.\n- **Left Workspace Rail**: claim controls, workspace tabs, and local Vertex runtime settings stay together on the left while outputs stay in the center.\n- **Architecture Popovers**: every architecture node explains why it exists, its role, and its output.\n\n## Highest-Value Additions\n\nThese are the additions that most improve the project grade and demo clarity:\n\n1. **Interactive agent layer**: the project now feels like an agent because users can ask questions instead of only reading a static review.\n2. **Human-in-the-loop controls**: the app demonstrates governance, not just automation.\n3. **Manager control room**: the MVP moves from a single-claim demo to an operations workflow.\n4. **Auditable outputs**: trace, approval log, and downloadable review package make the result explainable.\n5. **Live-ready architecture**: Vertex AI can be enabled later while deterministic tools keep demos reliable.\n\n## Repository Structure\n\n```text\n.\n|-- src/                         # Vercel / Next.js application source\n|   |-- app/                     # Next.js App Router pages, API route, global CSS\n|   |-- components/              # Interactive ClaimsOps UI components\n|   `-- lib/                     # JS claims engine, LLM providers, Vertex AI helper\n|-- claimsops/                   # Streamlit / Python implementation\n|   |-- app.py                   # Streamlit interface\n|   |-- core/                    # Deterministic engine and CrewAI adapter\n|   |-- demo_data/               # Demo policies, claims, history, requirements\n|   |-- requirements.txt         # Streamlit dependencies\n|   `-- requirements-crewai.txt  # Optional CrewAI + Vertex AI dependencies\n|-- docs/\n|   |-- agent.md                 # Continuation log and project evaluation\n|   |-- agent_skill_contract.md  # Agent/tool contract shown in the app\n|   |-- prompts_and_tools.md     # Prompt and tool pack\n|   `-- project/                 # Product and design guidance\n|-- .streamlit/                  # Streamlit theme config\n|-- .env.example                 # Optional local live-mode environment template\n|-- AGENTS.md                    # Instructions for future coding agents\n|-- next.config.mjs              # Next.js config\n|-- package.json                 # Vercel app scripts/dependencies\n|-- pnpm-lock.yaml               # Locked JS dependencies\n`-- vercel.json                  # Vercel build settings\n```\n\n## Run The Vercel App\n\nUse this for the polished web MVP and Vercel deployment.\n\n```powershell\npnpm install\npnpm dev\n```\n\nOpen:\n\n```text\nhttp://localhost:3000\n```\n\nProduction build check:\n\n```powershell\npnpm build\n```\n\n## Deploy To Vercel\n\n1. Import the GitHub repo `lukatcheishvili/claimsops-agent` in Vercel.\n2. Keep the root directory as the repository root.\n3. Vercel should auto-detect Next.js.\n4. Use:\n\n```text\nInstall Command: pnpm install\nBuild Command: pnpm build\nOutput Directory: .next\n```\n\nThe Vercel app uses the deterministic JavaScript claims engine in `src/lib/claimsEngine.js` as the source of truth. It also includes a server-side Vertex AI route at `src/app/api/claimsops/analyze/route.js`. When credentials are configured, the route calls Gemini on Vertex AI to generate a live adjuster-facing review while the deterministic tool output remains auditable.\n\n## Enable Vertex AI On Vercel\n\nThe app requests Vertex AI live mode by default. It will show **Ready** or **Live** only when the runtime also has valid service account credentials. It will show **Needs Credentials** if the project settings are present but the private key is missing.\n\nAdd these environment variables in **Vercel Project Settings -> Environment Variables**:\n\n```text\nGOOGLE_GENAI_USE_VERTEXAI=true\nGOOGLE_CLOUD_PROJECT=<your-project-id>\nGOOGLE_CLOUD_LOCATION=global\nVERTEX_AI_LIVE=true\nVERTEX_AI_MODEL=gemini-2.5-flash\nGOOGLE_SERVICE_ACCOUNT_JSON={...service account JSON...}\n```\n\nTo explicitly disable live mode for a fallback-only demo, set:\n\n```text\nVERTEX_AI_LIVE=false\n```\n\nThe service account must be allowed to call Vertex AI in your configured Google Cloud project. Do not commit the JSON key. After updating Vercel variables, redeploy the project. In the app, load or submit a claim and open **Agent Review**; the **Vertex AI Live Review** and **Vertex Runtime Status** panels will show either the live review or the exact fallback reason.\n\nThe app defaults to `global` and `gemini-2.5-flash` because current Google examples use the global Vertex endpoint for Gemini and older Gemini 2.0 Flash models have reached retirement.\n\nThe sidebar also has a **Vertex AI Config** box. Use it to enter runtime settings for a specific demo run. To clear **Needs Credentials**, paste a service account JSON value into the masked credential field or configure `GOOGLE_SERVICE_ACCOUNT_JSON` in Vercel. The sidebar credential is sent only for the active request and is not committed to the repo.\n\n## Choose An AI Provider\n\nThe Vercel app can generate the live adjuster review with **Vertex AI** or with a plain **API key** from another LLM. Pick one from the **Provider** dropdown in the left-rail config box:\n\n- **Vertex AI** — Google Cloud service account (existing path; uses the fields above).\n- **Google Gemini (API key)** — Google AI Studio key via the Generative Language API.\n- **OpenAI (API key)** — OpenAI Chat Completions (`sk-...` key).\n- **Anthropic Claude (API key)** — Anthropic Messages API key.\n\nFor the API-key providers, paste the key into the masked **API Key** field and optionally change the **Model**. The key is sent only for the active request and is never written to the repo. Deterministic tool output stays the source of truth; if the key is missing or the provider call fails, the app falls back to deterministic-only mode and shows the exact reason.\n\nFor deployments, the API-key providers also read these environment variables as a fallback when no key is pasted:\n\n```text\nGEMINI_API_KEY=...        # or GOOGLE_API_KEY / GOOGLE_GENERATIVE_AI_API_KEY\nOPENAI_API_KEY=sk-...\nANTHROPIC_API_KEY=...\n```\n\nDo not commit API keys or local `.env` files.\n\n## Run The Streamlit App\n\nUse this for the Python MVP and optional live CrewAI path.\n\n```powershell\npython -m venv .venv\n.venv\\Scripts\\python -m pip install -r claimsops\\requirements.txt\n.venv\\Scripts\\python -m streamlit run claimsops\\app.py\n```\n\nOpen:\n\n```text\nhttp://localhost:8501\n```\n\nIf port `8501` is busy, Streamlit may choose another port.\n\n## Optional CrewAI + Vertex AI Live Mode\n\nThe Streamlit app includes an optional CrewAI adapter. Deterministic mode remains the default so the class demo works without cloud credentials.\n\nInstall optional dependencies:\n\n```powershell\n.venv\\Scripts\\python -m pip install -r claimsops\\requirements-crewai.txt\n```\n\nCreate a local `.env` file from `.env.example`:\n\n```powershell\nCopy-Item .env.example .env\n```\n\nSet:\n\n```text\nUSE_CREWAI_LIVE=true\nGOOGLE_GENAI_USE_VERTEXAI=true\nGOOGLE_CLOUD_PROJECT=<your-project-id>\nGOOGLE_CLOUD_LOCATION=global\nCREWAI_MODEL=gemini/gemini-2.5-flash\n```\n\nAuthenticate with Google Cloud Application Default Credentials or a service account that can call Vertex AI:\n\n```powershell\ngcloud auth application-default login\ngcloud config set project <your-project-id>\ngcloud services enable aiplatform.googleapis.com\n```\n\nRestart Streamlit after changing `.env`. The sidebar should show `Live mode: True`.\n\n## Main Workflows\n\n1. **Submit Claim**: load a sample, enter a claim manually, or use the evidence upload simulation.\n2. **Agent Chat Rail**: ask the ClaimsOps agent why it chose a route, what evidence is missing, how risk was scored, or how the architecture works from the right-side chat rail. Drag the rail's left edge to give the chatbot more room, or use the canvas chat toggle to hide it.\n3. **Agent Review**: show the recommendation, risk score drivers, coverage logic, evidence logic, history context, Vertex status, and audit trace.\n4. **Communications**: review customer and adjuster drafts, then simulate human approval, evidence request, or manual escalation.\n5. **Operations Dashboard**: inspect queue KPIs, severity distribution, risk vs exposure, evidence readiness, owner workload, and the claims table.\n6. **Manager View**: review highest-value operational blockers, urgent SLAs, owner load, and queue actions.\n7. **Architecture**: hover over each node to explain the multi-agent workflow and human-in-the-loop control model.\n8. **Prompt Pack**: show the agent prompt, tool contract, and guardrails.\n\n## Agent Design\n\nClaimsOps Agent uses specialist agents:\n\n- Claims Intake Agent\n- Coverage Verification Agent\n- Evidence Review Agent\n- Risk and Fraud Triage Agent\n- Communication Agent\n- Supervisor Agent\n\nTools provide structured facts: policy lookup, claim history, document requirements, risk scoring, next-action routing, and communication drafting. The supervisor agent recommends a route, but final insurance decisions remain with a human adjuster.\n\n## Safety Guardrails\n\n- No automated claim approval, denial, settlement, payment, or fraud accusation.\n- Human approval is required for high-impact decisions.\n- Demo mode minimizes personally identifiable information.\n- Tool results are treated as the source of truth for policy, evidence, history, and risk checks.\n- Local secrets belong in `.env` or deployment secrets, never in Git.\n\n## Project Guidance\n\nBefore changing product behavior or UI, read:\n\n- `docs/agent.md`\n- `docs/project/PRODUCT.md`\n- `docs/project/DESIGN.md`\n- `AGENTS.md`\n- `docs/agent_skill_contract.md`\n- `docs/prompts_and_tools.md`\n\n## Verification Checklist\n\nRun these before pushing meaningful changes:\n\n```powershell\npnpm build\n.venv\\Scripts\\python -m py_compile claimsops\\app.py claimsops\\core\\engine.py claimsops\\core\\crewai_adapter.py\nrg -n --glob '!README.md' --glob '!AGENTS.md' \"transition:\\s*all|outline:\\s*none|outline-none|user-scalable|maximum-scale|onPaste\" claimsops src .streamlit docs -S\n```\n\nFor UI changes, also verify:\n\n- Vercel app responds at `http://localhost:3000`.\n- Streamlit app responds at its local port.\n- Sidebar selected claim text is readable.\n- Estimated claim amount input does not prepend `0`.\n- Submitted evidence labels are human readable.\n- Right-side Agent Chat rail can answer evidence, risk, coverage, route, Vertex, and audit questions, provide compact visual answer cards, resize by dragging its left edge, and be hidden with the canvas chat toggle.\n- Dashboard charts render in dark theme.\n- Architecture workflow lines, nodes, and popovers do not overlap.\n\n## Team\n\n- Shreya Jha\n- Claudia Aranguren Moliner\n- Luka Tcheishvili\n- Mohammad Alkhan\n- Ghezlan Almatar\n","readmeExcerpt":"ClaimsOps Agent **Live Demo:** $1 Agentic AI MVP for **Insurance Claims Operations**. ClaimsOps Agent demonstrates how a multi-agent workflow can intake a claim, verify coverage, inspect evidence, score operational risk, recommend the next action, draft communications, and keep final insurance decisions human-gated. The repo contains two working interfaces: - **Vercel / Next.js app**: polished web MVP for deployment ","codeSnippets":[],"executableExamples":[{"language":"text","snippet":".\n|-- src/                         # Vercel / Next.js application source\n|   |-- app/                     # Next.js App Router pages, API route, global CSS\n|   |-- components/              # Interactive ClaimsOps UI components\n|   `-- lib/                     # JS claims engine, LLM providers, Vertex AI helper\n|-- claimsops/                   # Streamlit / Python implementation\n|   |-- app.py                   # Streamlit interface\n|   |-- core/                    # Deterministic engine and CrewAI adapter\n|   |-- demo_data/               # Demo policies, claims, history, requirements\n|   |-- requirements.txt         # Streamlit dependencies\n|   `-- requirements-crewai.txt  # Optional CrewAI + Vertex AI dependencies\n|-- docs/\n|   |-- agent.md                 # Continuation log and project evaluation\n|   |-- agent_skill_contract.md  # Agent/tool contract shown in the app\n|   |-- prompts_and_tools.md     # Prompt and tool pack\n|   `-- project/                 # Product and design guidance\n|-- .streamlit/                  # Streamlit theme config\n|-- .env.example                 # Optional local live-mode environment template\n|-- AGENTS.md                    # Instructions for future coding agents\n|-- next.config.mjs              # Next.js config\n|-- package.json                 # Vercel app scripts/dependencies\n|-- pnpm-lock.yaml               # Locked JS dependencies\n`-- vercel.json                  # Vercel build settings"},{"language":"powershell","snippet":"pnpm install\npnpm dev"},{"language":"text","snippet":"http://localhost:3000"},{"language":"powershell","snippet":"pnpm build"},{"language":"text","snippet":"Install Command: pnpm install\nBuild Command: pnpm build\nOutput Directory: .next"},{"language":"text","snippet":"GOOGLE_GENAI_USE_VERTEXAI=true\nGOOGLE_CLOUD_PROJECT=<your-project-id>\nGOOGLE_CLOUD_LOCATION=global\nVERTEX_AI_LIVE=true\nVERTEX_AI_MODEL=gemini-2.5-flash\nGOOGLE_SERVICE_ACCOUNT_JSON={...service account JSON...}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"Agentic AI MVP for insurance claims operations. A multi-agent workflow intakes a claim, verifies coverage, inspects evidence, scores operational risk, recommends the next action and drafts communications — while keeping final decisions human-gated. Built as both a Next.js web app and a Streamlit + CrewAI implementation. ClaimsOps Agent **Live Demo:** $1 Agentic AI MVP for **Insurance Claims Operations**. ClaimsOps Agent demonstrates how a multi-agent workflow can intake a claim, verify coverage, inspect evidence, score operational risk, recommend the next action, draft communications, and keep final insurance decisions human-gated. The repo contains two working interfaces: - **Vercel / Next.js app**: polished web MVP for deployment","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":402,"uniquenessScore":66,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T18:14:05.230Z","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":"2026-10-09T18:14:05.230Z","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":"2026-10-10T02:03:03.114Z","emptyReason":null},"items":[{"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":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"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":"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_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}