{"id":"b73c5752-6060-4b28-8c18-b5b651b7ba65","entityType":"agent","slug":"crewai-rahil1801-ai-ops-assistant","name":"ai_ops_assistant","canonicalUrl":"https://www.xpersona.co/agent/crewai-rahil1801-ai-ops-assistant","canonicalPath":"/agent/crewai-rahil1801-ai-ops-assistant","generatedAt":"2026-10-09T14:23:55.312Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-05-19T06:58:55.756Z","emptyReason":null},"description":"A multi-agent AI system built following CrewAI-inspired Agent Architecture patterns that accepts natural-language tasks, automatically plans execution steps, calls real-world APIs/tools, verifies results, and returns structured answers through an interactive Streamlit interface. This project follows the CrewAI architectural pattern. AI Operations Assistant A **multi-agent AI system** built following **CrewAI-inspired Agent Architecture patterns** that accepts natural-language tasks, automatically plans execution steps, calls real-world APIs/tools, verifies results, and returns structured answers through an interactive Streamlit interface. **Note** This project follows the **CrewAI architectural pattern (Planner → Executor → Verifier)** using a *","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 5/19/2026.","installCommand":"git clone https://github.com/rahil1801/ai_ops_assistant.git","sourceUrl":"https://github.com/rahil1801/ai_ops_assistant","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/rahil1801/ai_ops_assistant","kind":"source"}],"safetyScore":66,"overallRank":18.6,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"A multi-agent AI system built following CrewAI-inspired Agent Architecture patterns that accepts natural-language tasks, automatically plans execution steps, ca"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-05-19T06:58:55.756Z","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":"2026-05-19T06:58:55.756Z","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":"2026-05-19T06:58:55.756Z","emptyReason":null},"lastUpdatedAt":"2026-05-19T06:58:55.756Z","lastCrawledAt":"2026-05-19T06:58:55.756Z","lastIndexedAt":null,"nextCrawlAt":"2026-05-26T06:58:55.756Z","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/rahil1801/ai_ops_assistant.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/crewai-rahil1801-ai-ops-assistant/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-09T14:23:55.311Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-rahil1801-ai-ops-assistant/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":"2026-05-19T06:58:55.756Z","emptyReason":null},"readme":"# AI Operations Assistant\n\nA **multi-agent AI system** built following **CrewAI-inspired Agent Architecture patterns** that accepts natural-language tasks, automatically plans execution steps, calls real-world APIs/tools, verifies results, and returns structured answers through an interactive Streamlit interface.\n\n> **Note**  \n> This project follows the **CrewAI architectural pattern (Planner → Executor → Verifier)** using a **custom lightweight implementation**.  \n> It mirrors CrewAI’s design principles while remaining framework-agnostic and ideal for educational and assignment purposes.\n\n---\n\n## Features\n\n- **Multi-Agent Architecture**\n  - Planner, Executor, and Verifier agents working together\n- **LLM-Powered Reasoning**\n  - Supports **Gemini**, **Groq (FREE)**, and **OpenRouter**\n- **Tool-Augmented Intelligence**\n  - GitHub, Weather, Currency, News, StackOverflow APIs\n- **Conversational Memory**\n  - Understands follow-up questions and context\n- **Streamlit UI**\n  - Clean, modern UI with step-by-step transparency\n- **Robust Error Handling**\n  - Graceful failures, partial results, validation checks\n\n---\n\n## 🧠 Architecture Overview\n\n- ai_ops_assistant/\n  - agents/ #**consists of agents**\n  - llm/ #**consists of LLMs (Gemini, Groq, OpenRouter)**\n  - memory/ #**consists of memory logic for context**\n  - tools/ #**consists of third party tools for LLMs**\n  - .env.example\n  - main.py\n  - README.md\n  - requirements.txt\n- venv/\n\n\n---\n\n##  Architecture Explanation\n\nThe **AI Operations Assistant** is designed as a **layered, agent-based architecture** inspired by CrewAI principles.  \nInstead of treating the AI as a single monolithic chatbot, the system decomposes intelligence into **specialized components**, each with a clear responsibility.\n\nThis architecture improves **reasoning quality**, **debuggability**, **extensibility**, and **real-world reliability**.\n\n---\n\n## 1. High-Level Architecture\n\n\nAt a high level, the system converts **natural language → structured plan → real execution → verified output**.\n\n---\n\n## 2. Architectural Layers\n\n### 2.1 Presentation Layer (Streamlit UI)\n\n**Responsibility**\n- Accept user input\n- Display execution plans, intermediate steps, and final results\n- Provide configuration options (LLM provider, API status)\n\n**Why Streamlit**\n- Rapid prototyping\n- Single-command deployment\n- Clean chat-based interaction\n- Ideal for demos and assignments\n\nThe UI itself is **stateless**, while conversation state is managed via Streamlit session state.\n\n---\n\n### 2.2 Memory Layer\n\n**Component**\n- `build_conversation_context()`\n\n**Responsibility**\n- Construct short-term conversational memory\n- Provide context for follow-up questions\n- Maintain continuity across turns\n\n**Design Choice**\n- Session-based memory (no database)\n- Lightweight and fast\n- Avoids long-term storage complexity\n\nThis layer ensures the system understands queries like:\n> “Tell me more about that”  \n> “Do the same for London”\n\n---\n\n### 2.3 Agent Orchestrator Layer\n\n**Component**\n- `AgentOrchestrator`\n\n**Responsibility**\n- Coordinate the entire agent workflow\n- Pass outputs between agents\n- Track execution state and errors\n- Maintain separation of concerns\n\nThe orchestrator acts as the **control plane** of the system.\n\n---\n\n## 3. Agent-Based Reasoning Layer\n\n### 3.1 Planner Agent\n\n**Role**\n- Converts unstructured user input into a structured execution plan\n\n**Responsibilities**\n- Understand intent using LLM reasoning\n- Break tasks into ordered steps\n- Decide which tools are required\n- Output a JSON-based execution plan\n\n**Why This Matters**\n- Prevents hallucinated answers\n- Makes AI reasoning explicit and inspectable\n- Enables deterministic execution\n\n---\n\n### 3.2 Executor Agent\n\n**Role**\n- Executes the plan created by the Planner Agent\n\n**Responsibilities**\n- Call external APIs and tools\n- Handle retries and failures\n- Collect raw results\n- Execute steps sequentially\n\n**Design Benefits**\n- Tool-agnostic execution\n- Easy to add new tools\n- Clear separation between reasoning and action\n\n---\n\n### 3.3 Verifier Agent\n\n**Role**\n- Validate and finalize results\n\n**Responsibilities**\n- Check completeness and correctness\n- Detect partial or failed executions\n- Assign execution status (`complete`, `partial`, `failed`)\n- Format the final user-facing output\n\n**Why Verification Is Critical**\n- Prevents misleading results\n- Improves trustworthiness\n- Makes the system more production-like\n\n---\n\n## 4. LLM Abstraction Layer\n\n**Component**\n- `BaseLLMClient`\n\n**Purpose**\n- Abstract away differences between LLM providers\n- Allow runtime switching of models\n\n**Supported Providers**\n- Gemini (Google)\n- Groq (FREE, ultra-fast)\n- OpenRouter (multi-model gateway)\n\n**Architectural Advantage**\n- Vendor-agnostic\n- Easy experimentation\n- Future-proof design\n\n---\n\n## 5. Tooling Layer\n\nEach tool implements a **standard interface**, enabling the Executor Agent to use them interchangeably.\n\n**Characteristics**\n- Modular\n- Extensible\n- Isolated from agent logic\n\n**Examples**\n- GitHub Tool → Repository & user data\n- Weather Tool → Forecasts (Open-Meteo)\n- Currency Tool → Exchange rates\n- News Tool → Headlines & articles\n- StackOverflow Tool → Developer Q&A\n\nThis design allows new tools to be added **without modifying agent logic**.\n\n---\n\n## 6. Data Flow Summary\n\n1. User submits a natural-language request\n2. Memory context is built from previous turns\n3. Planner Agent generates a structured plan\n4. Executor Agent performs real API calls\n5. Verifier Agent validates results\n6. Structured response is returned to UI\n\nThis ensures the system behaves as an **autonomous reasoning pipeline**, not a simple text generator.\n\n---\n\nThis architecture demonstrates how **modern agentic AI systems** are built in practice — combining LLM reasoning, tools, memory, and verification into a cohesive system.\n\n##  Agent Workflow\n\n1. **User Input**\n   - Natural language task submitted via Streamlit UI\n\n2. **Planner Agent**\n   - Understands user intent\n   - Generates a structured JSON execution plan\n   - Decides which tools are required\n\n3. **Executor Agent**\n   - Executes each step sequentially\n   - Calls external APIs and tools\n   - Collects raw results\n\n4. **Verifier Agent**\n   - Validates outputs\n   - Detects missing or partial data\n   - Produces final structured response with status\n\n---\n\n##  LLM Providers\n\nThe system abstracts LLMs behind a common interface (`BaseLLMClient`).\n\n### 1️⃣ Gemini (Google AI)\n- High-quality reasoning\n- API Key: `GEMINI_API_KEY`\n- Get key: https://makersuite.google.com/app/apikey\n\n### 2️⃣ Groq (FREE OpenAI Alternative)\n- Ultra-fast inference\n- Completely free (no credit card)\n- Uses LLaMA 3 models\n- API Key: `GROQ_API_KEY`\n- Get key: https://console.groq.com\n\n### 3️⃣ OpenRouter\n- Access 300+ models (GPT-4, Claude, Gemini, etc.)\n- API Key: `OPENROUTER_API_KEY`\n- Get key: https://openrouter.ai\n\n---\n\n## Memory System\n\n- Builds short-term conversational memory from previous messages\n- Enables:\n  - Follow-up questions\n  - Contextual understanding\n  - Natural dialogue flow\n- Memory is **session-based** (no long-term persistence)\n\n---\n\n##  Integrated Tools / APIs\n\n###  GitHub Tool\n- Search repositories\n- Fetch repository details\n- Get user profiles  \n**Optional:** `GITHUB_TOKEN` for higher rate limits\n\n###  Weather Tool\n- Current weather\n- 5-day forecasts\n- Powered by **Open-Meteo**\n- No API key required\n\n###  Currency Tool\n- Currency conversion\n- Live exchange rates\n\n###  News Tool\n- Search news articles\n- Fetch top headlines\n- Requires `GNEWS_API_KEY`\n\n###  StackOverflow Tool\n- Search programming questions\n- Retrieve answers\n- Useful for debugging and learning\n\n---\n\n## ⚡ Quick Start (On LocalHost using CLI)\n\n### 1. Clone this repo and install dependencies\n\n```bash\ngit clone https://github.com/rahil1801/ai_ops_assistant.git\n\npython -m venv venv (only if virtual environment is not created)\n\n# MACOS\nsource venv/bin/activate  \n\n# Windows\nvenv\\Scripts\\activate\n\ncd ai_ops_assistant\n\npip install -r requirements.txt\n```\n\n### 2. Setup Environment Variables\n\n```bash\n# Create an .env file and copy environment variables from .env.example\n\nGEMINI_API_KEY = your-api-key\nGROQ_API_KEY = your-api-key\nOPENROUTER_API_KEY = your-api-key (Make sure prompts are available to train their models to use for free)\n\nGITHUB_TOKEN = your-api-key (Make sure to give appropriate permissions)\nGNEWS_API_KEY = your-api-key\n\n```\n\n### 3. We are almost there. Now run the project\n\n```bash\n\nstreamlit run main.py\n\n```\n\n## ⚡ Quick Start (From Deployed project on Streamlit)\n\nThis project is deployed on streamlit so that users can check it to avoid all the necessary setup required to run it from terminal.\n\nLink to project: https://aioperationsassistant.streamlit.app/\n\n---\n\n### 🧪 Example Tasks\n\n- “Find top Python ML repositories on GitHub”\n\n- “What’s the weather in New York and London?”\n\n- “Convert 100 USD to EUR”\n\n- “Search StackOverflow for Python async issues”\n\n- “Get latest AI news”\n\n- Follow-up queries are supported naturally.\n\n---\n\n### 🧯 Error Handling\n\n- Automatic retries for tool/API failures\n\n- Partial result support\n\n- Verifier agent detects inconsistencies\n\n- User-friendly error messages\n\n---\n\n### 📈 Future Improvements\n\n- Parallel tool execution\n\n- Caching (Redis)\n\n- Cost & token tracking\n\n- More tools (Stocks, Maps, Finance)\n\n- User authentication and history persistence\n\n## ⚠️ Limitations and Trade-offs\n\nWhile the **AI Operations Assistant** demonstrates a robust multi-agent architecture, certain limitations and trade-offs were intentionally accepted to keep the system lightweight, understandable, and suitable for educational use.\n\n---\n\n## 1. No True Parallel Agent Execution\n\n**Limitation**\n- Agents execute **sequentially** (Planner → Executor → Verifier)\n- Tool calls are not parallelized\n\n**Trade-off**\n- ✔ Simpler execution flow\n- ✔ Easier debugging and traceability\n- ❌ Slower for multi-tool or large tasks\n\n**Reasoning**\nParallel execution adds complexity (async orchestration, race conditions) and was avoided to prioritize clarity and correctness.\n\n---\n\n## 2. Session-Based Memory Only\n\n**Limitation**\n- Memory exists only for the current session\n- No long-term or persistent memory\n\n**Trade-off**\n- ✔ No database or storage overhead\n- ✔ Faster and simpler design\n- ❌ Context is lost on refresh or restart\n\n**Reasoning**\nPersistent memory requires storage, embeddings, and retrieval logic, which was out of scope for this implementation.\n\n---\n\n## 3. Dependency on LLM Output Quality\n\n**Limitation**\n- Planner reasoning depends heavily on LLM accuracy\n- Incorrect plans may lead to suboptimal execution\n\n**Trade-off**\n- ✔ Flexible and intelligent planning\n- ❌ Non-deterministic behavior\n\n**Reasoning**\nThis reflects real-world agentic systems, where verification mitigates but does not eliminate LLM uncertainty.\n\n---\n\n## 4. Limited Tool Coverage\n\n**Limitation**\n- Only a fixed set of tools is available\n- Cannot handle domains without a defined tool\n\n**Trade-off**\n- ✔ Clear and controlled execution environment\n- ✔ Easier to validate outputs\n- ❌ Reduced domain coverage\n\n**Reasoning**\nEach tool requires careful validation; adding more tools was deferred in favor of architectural soundness.\n\n---\n\n## 5. Sequential Tool Execution\n\n**Limitation**\n- Tools are executed one step at a time\n\n**Trade-off**\n- ✔ Predictable results\n- ✔ Easier error handling\n- ❌ Increased latency\n\n**Reasoning**\nSequential execution simplifies orchestration and ensures deterministic step ordering.\n\n---\n\n## Summary\n\nThese limitations reflect **conscious design decisions**, not architectural weaknesses.  \nThe project focuses on demonstrating **agentic reasoning, tool grounding, and architectural clarity**, which are foundational concepts for building production-grade AI systems.\n\nMany of these trade-offs can be addressed in future iterations without changing the core architecture.","readmeExcerpt":"AI Operations Assistant A **multi-agent AI system** built following **CrewAI-inspired Agent Architecture patterns** that accepts natural-language tasks, automatically plans execution steps, calls real-world APIs/tools, verifies results, and returns structured answers through an interactive Streamlit interface. **Note** This project follows the **CrewAI architectural pattern (Planner → Executor → Verifier)** using a *","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"git clone https://github.com/rahil1801/ai_ops_assistant.git\n\npython -m venv venv (only if virtual environment is not created)\n\n# MACOS\nsource venv/bin/activate  \n\n# Windows\nvenv\\Scripts\\activate\n\ncd ai_ops_assistant\n\npip install -r requirements.txt"},{"language":"bash","snippet":"# Create an .env file and copy environment variables from .env.example\n\nGEMINI_API_KEY = your-api-key\nGROQ_API_KEY = your-api-key\nOPENROUTER_API_KEY = your-api-key (Make sure prompts are available to train their models to use for free)\n\nGITHUB_TOKEN = your-api-key (Make sure to give appropriate permissions)\nGNEWS_API_KEY = your-api-key"},{"language":"bash","snippet":"streamlit run main.py"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"A multi-agent AI system built following CrewAI-inspired Agent Architecture patterns that accepts natural-language tasks, automatically plans execution steps, calls real-world APIs/tools, verifies results, and returns structured answers through an interactive Streamlit interface. This project follows the CrewAI architectural pattern. AI Operations Assistant A **multi-agent AI system** built following **CrewAI-inspired Agent Architecture patterns** that accepts natural-language tasks, automatically plans execution steps, calls real-world APIs/tools, verifies results, and returns structured answers through an interactive Streamlit interface. **Note** This project follows the **CrewAI architectural pattern (Planner → Executor → Verifier)** using a *","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":408,"uniquenessScore":61,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-05-19T06:58:55.756Z","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":"2026-05-19T06:58:55.756Z","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":"2026-10-09T14:23:55.312Z","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"}]}}}