{"id":"f3ac7871-af96-46b9-a7b1-31f7e6c7672f","entityType":"agent","slug":"crewai-ri-yan-agentic-ai-base","name":"Agentic-AI-Base","canonicalUrl":"https://www.xpersona.co/agent/crewai-ri-yan-agentic-ai-base","canonicalPath":"/agent/crewai-ri-yan-agentic-ai-base","generatedAt":"2026-10-09T05:46:16.565Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"Analytics-focused conversational agent framework supporting LangChain, LangGraph, and CrewAI. Generates validated chart/dashlet payloads and query templates from natural language. Genric Agents **Purpose:** This repository implements **Jobseekers**, a job search conversational agent that analyzes resume information and user queries to provide personalized job recommendations and even apply to roles on the user’s behalf. It supports multiple agent frameworks — **LangChain**, **LangGraph**, and **CrewAI** — and follows a modular architecture that separates concerns across API, agent orchestratio","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":null,"sourceUrl":"https://github.com/Ri-yan/Agentic-AI-Base","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/Ri-yan/Agentic-AI-Base","kind":"source"}],"safetyScore":66,"overallRank":18,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Analytics-focused conversational agent framework supporting LangChain, LangGraph, and CrewAI. Generates validated chart/dashlet payloads and query templates fro"},"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":"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":"2026-04-15T05:21:22.124Z","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":"2026-02-25T05:06:58.816Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-02-25T05:06:58.816Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-04T05:06:58.816Z","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-ri-yan-agentic-ai-base/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-09T05:46:16.565Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-ri-yan-agentic-ai-base/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":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"# Genric Agents\n\n> **Purpose:** This repository implements **Jobseekers**, a job search conversational agent that analyzes resume information and user queries to provide personalized job recommendations and even apply to roles on the user’s behalf.  \n\nIt supports multiple agent frameworks — **LangChain**, **LangGraph**, and **CrewAI** — and follows a modular architecture that separates concerns across API, agent orchestration, tools, and use-cases.\n---\n\n## Table of contents\n\n1. Project overview\n2. Quickstart (run locally)\n3. Environment & configuration\n4. API endpoints (examples)\n5. High-level architecture (ASCII diagram)\n6. Component-by-component breakdown\n7. JobHuntings use-case: flow and templates\n8. Models, validators & tools\n9. How the agent is constructed (agent factory / selectors)\n10. Logging, guardrails & memory\n11. Tests, debugging & troubleshooting\n12. Deployment & production notes\n13. Extensions, improvements & TODOs\n\n---\n[![Agents](https://github.com/user-attachments/assets/1edea1e9-e1c5-4e35-81e3-b4acc7d57b44)](https://github.com/Ri-yan/Agentic-AI-Base)\n\n\n## 1. Project overview\n\nThis project provides a modular agent platform focused on job helping buddy. The major goals:\n\n* Accept a user prompt + schema  JSON payloads.\n* Validate model outputs with Pydantic models (SchemaModel, GraphDataModel, QueryConfigModel).\n* Support multiple underlying agent runtimes (LangChain, LangGraph, CrewAI).\n* Provide pluggable tools  and memory backends.\n\nKey strengths:\n\n* Clear separation of concerns (API ↔ usecases ↔ agent wrapper ↔ tools ↔ LLM)\n* Pydantic-based validation for deterministic outputs\n* Flexible agent factory to plug different frameworks\n\n## 2. Quickstart (run locally)\n\n**Prerequisites**\n\n* Python 3.11+\n* An OpenAI API key (or other model provider depending on your AGENT\\_FRAMEWORK)\n\n**Install**\n\n```bash\n# create conda env (recommended)\nconda create -n genric-agents python=3.11 -y\nconda activate genric-agents\n\n# install dependencies\npip install -r requirements.txt\n\n```\n\n**Set environment variables** (example):\n\n```bash\nexport OPENAI_API_KEY=\"sk-...\"\nexport AGENT_FRAMEWORK=langgraph   # or langchain / crewai\nexport OPENAI_MODEL=gpt-4o-mini\n```\n\n**Run the API**\n\n```bash\n# option A: run directly\npython main.py\n# option B: uvicorn\nuvicorn main:app --reload --port 8025\n```\n\nThe app will be available at `http://localhost:8025`.\n\n## 3. Environment & configuration\n\nThe project loads environment variables from `resources/config.env` via `resources/constant.load_environs()`.\n\nImportant variables:\n\n* `AGENT_FRAMEWORK` — one of `langchain`, `langgraph`, `crewai`. Determines which agent implementation is used.\n* `OPENAI_API_KEY` — required for OpenAI-based LLM usage.\n* `OPENAI_MODEL` — model name (e.g. `gpt-4o-mini`).\n* `MULTI_NODE_AGENT` — (project-specific) toggle for multi-node behavior.\n\n**Agent config files** are in `config/agents/` (e.g. `analytics_agent_config.json`). These files define agent identity, guardrails, topics and capabilities used by the agent factory.\n\n## 4. API endpoints (examples)\n\n`POST /api/agent/chat` — main entrypoint for session-based agent runs.\n\n* Request model: `AgentQuery` (fields: `sessionId`, `prompt`, `payload`)\n\nExample `curl` request:\n\n```bash\ncurl -X POST http://localhost:8025/api/agent/chat \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"sessionId\": \"session-123\",\n    \"prompt\": \"Show me monthly leads by source\",\n    \"payload\": {\n      \"details\": {\"table_name\":\"view\",\"fields\":[]},\n      \"query\": \"monthly leads split by source\"\n    }\n  }'\n```\n\n`POST /api/genai/run` — directly invokes the `JobHuntingsUseCase` with arbitrary dict payload for quick testing.\n\nResponse shape (standardized by `utilities.response.build_response`):\n\n```json\n{\n  \"status\": true,\n  \"message\": \"\",\n  \"response\": {\n     \"Data\": {...},\n     \"AIMessage\": \"...\",\n     \"ToolMessage\": \"...\",\n     \"Reasoning\": \"...\"\n  }\n}\n```\n\n## 5. High-level architecture (ASCII diagram)\n\n```\n+----------+    HTTP   +----------------+    create/get    +--------------------+\n|  Client  | ----->   | FastAPI (main) | --------------->  | Agent Manager /     |\n+----------+          +----------------+                   |  BaseAgent          |\n                                                           +--------------------+\n                                                                    |\n                                                                    | selects\n                                                                    v\n                                               +-------------------------------------------+\n                                               | Agent Selector (LangChain / LangGraph /   |\n                                               |  CrewAI) -> returns a framework-specific   |\n                                               |  agent wrapper (LangChainAgentWrapper etc.)|\n                                               +-------------------------------------------+\n                                                                    |\n                                             +----------------------+-----------------+\n                                             |                                        |\n                                         LLM / Guardrails                      Tools & Memory\n                                       (create_llm via llm_factory)          (tool_factory, memory_factory)\n                                             |                                        |\n                                             v                                        v\n                                 +---------------------------+           +-----------------------------+\n                                 | Use Case / Prompt Chains  | <-------> | Tool implementations (,\n                                 | ()|           |  ) |\n                                 +---------------------------+           +-----------------------------+\n                                                                    |\n                                                                    v\n                                                           +--------------------+\n                                                           | Validators (pydantic)|\n                                                           +--------------------+\n                                                                    |\n                                                                    v\n                                                           +--------------------+\n                                                           |  API returns JSON   |\n                                                           +--------------------+\n```\n\n## 6. Component-by-component breakdown\n\n**`main.py`**\n\n* FastAPI entry with `app.include_router(routes, prefix='/api')`. Starts uvicorn.\n\n**`api/routes.py`**\n\n* Defines REST endpoints `/agent/chat` and `/genai/run`.\n* Uses `services.agent_executor.run_agent_query` for session-based calls.\n\n**`services/agent_executor.py`**\n\n* Thin shim that calls `agents_builder.agent_manager.get_agent` (factory) and `agent.run(...)`.\n\n**`agents_builder/`**\n\n* `agent_config_loader.py` — loads JSON agent configs from `config/agents/`.\n* `agent_manager.py` — creates and caches agents per session (in-memory `agent_store`). Wraps tools to match differing tool signatures across frameworks.\n* `base_agent.py` — constructs the agent implementation using `agents_builder.selector.select_agent`.\n* `tool_factory.py` — adapts local Python functions into framework-specific tools (LangChain `Tool`, CrewAI `BaseTool`, etc.).\n* `memory_factory.py` — provides memory backends for each supported framework (LangChain conversation memory or CrewAI memory wrappers).\n* `selector/` — contains per-framework constructors: `langchain_selector.py`, `langgraph_selector.py`, `crewai_selector.py`. Each wraps the LLM, memory and tools into a framework-specific agent and exposes a unified `run` interface.\n\n\n**`tools/`**\n\n* Global tools that can be mounted onto agents: `various tools`. These call into the JobsHunting generator or other helpers.\n\n**`resources/`**\n\n* `config.env` default env variables\n* Logging helpers `resources/Logging/studio_logger.py`\n\n**`utilities/response.py`**\n\n* Standardized response builder used across wrappers.\n\n## 7. JobsHunting use-case: flow and templates\n\nCore flow (inside `JobsHuntingGenerator`):\n\nThe use-case uses multiple templated prompts (in `templates/`) to keep each step focused and reproducible.\n\n## 8. Models, validators & tools\n\n**Pydantic models** (key ones):\n\n**Validators** ensure the LLM outputs strictly conform to the expected schema; they also strip markdown/code fences commonly emitted by LLMs.\n\n**Tools**\n\n* `fields_filter_tool` — simple keyword partial-matching filter that returns candidate field definitions.\n\n## 9. How the agent is constructed (agent factory / selectors)\n\nFlow when a request comes in:\n\n1. `services.agent_executor.run_agent_query` calls `agents_builder.get_agent` (see `agent_manager.py`).\n2. The agent manager: loads config (per-agent or default), selects tools from `tools.ALL_TOOLS`, wraps them to framework-compatible signatures, then constructs a `BaseAgent(config, tools)` instance.\n3. `BaseAgent` delegates to `agents_builder.selector.select_agent` which returns a framework-specific wrapper (LangChainAgentWrapper, LangGraphAgentWrapper or CrewAIAgentWrapper).\n4. Wrapper initializes an LLM (via `llm.llm_factory.create_llm`), memory (via `memory_factory`) and constructs agent internals (chains, tools, guardrails, system prompt).\n5. When `agent.run(prompt, payload)` is called, the wrapper executes the agent flow and returns a standardized response using `utilities.response.build_response`.\n\n## 10. Logging, guardrails & memory\n\n* **Guardrails**: `guardrails/sys_guards.py` contains a system-level instruction applied to agents to reduce hallucinations and enforce step-by-step reasoning.\n* **Logging**: `resources/Logging/studio_logger.py` returns a simple Python `logging` instance per use-case.\n* **Memory**: `agents_builder/memory_factory.py` adapts either LangChain conversation memories or CrewAI memory classes. Currently the project ships with adapters to produce conversation buffers or long-term memory where available.\n\n## 11. Tests, debugging & troubleshooting\n\n**Common issues & fixes**\n\n* `OPENAI_API_KEY` not found: ensure `resources/config.env` is filled or set environment variables before starting.\n* `AGENT_FRAMEWORK` mismatch: set `AGENT_FRAMEWORK` to one of `langchain`, `langgraph`, `crewai`. If a framework is missing in your environment (e.g. `crewai` not installed), either install it or pick another framework.\n* Import errors (langchain/langgraph version mismatches): ensure versions in `requirements.txt` are installed. LangChain/LangGraph have breaking changes across major versions — pin the working versions from `requirements.txt`.\n* LLM output formatting errors: validators may raise when the LLM returns non-JSON results. Inspect `templates/` to tune instructions and add stricter output schema.\n\n**Debugging tips**\n\n* Enable debug logs via python logging configuration.\n* Run `uvicorn main:app --reload` and call endpoints with simple payloads first.\n* Re-run a failing step manually: the  class exposes `_generate_chain_run` type methods — wrap them to print raw LLM output to debug.\n\n## 12. Deployment & production notes\n\n* **Secrets**: never store `OPENAI_API_KEY` in repo. Use secret stores (AWS Secrets Manager, HashiCorp Vault) in production.\n* **Scaling**: the agent store is an in-memory dict. For multiple instances / horizontal scaling, move session storage to Redis or a persistent store and share agent state or only store immutable configs in DB.\n* **Rate limiting & concurrency**: LLM calls are rate-limited and can be slow. Add request queuing, timeouts and circuit-breakers around LLM calls.\n* **Persistent memory**: For long-term memory or multi-session context, integrate a vector DB (Weaviate, Pinecone, Chroma) and adapt `memory_factory` to use it.\n* **Observability**: add structured traces around LLM calls and tool calls (e.g. OpenTelemetry), and log LLM tokens usage for cost control.\n\n## 13. Extensions, improvements & TODOs\n\n**Short-term**\n\n* Add unit tests for `validators._validate_model` and `fields_filter_tool`.\n* Harden prompt templates (provide examples and negative examples to reduce hallucination).\n* Add request/response tracing (e.g. request ID headers).\n\n**Medium-term**\n\n* Add a vector store backed memory implementation and persistence across restarts.\n* Add a dashboard showing recent sessions, requests and token usage.\n* Add more sophisticated field matching (fuzzy match, name synonyms, embedding-based similarity).\n\n**Long-term / Research**\n\n* Multi-agent coordination: compose multiple agents (ETL-agent, Query-agent, Viz-agent) into pipelines.\n* Offline deterministic generation: explore using function-calling APIs or structured output specs to guarantee correct JSON output.\n\n---\n\n## Appendix: file map (important files)\n\n```\nmain.py                          # FastAPI entry\napi/routes.py                    # API endpoints\nagents_builder/                  # Agent factory, tool adapter, memory adapter\n  - agent_manager.py\n  - base_agent.py\n  - tool_factory.py\n  - memory_factory.py\n  - selector/ (langchain, langgraph, crewai)\nusecases/agents/          # agents use-case, templates, validators\ntools/                           # application-level tools mounted into agents\nresources/                       # config.env + logging\nutilities/response.py            # standard response format\nconfig/agents/analytics_agent_config.json  # agent metadata and guardrails\n```\n\n","readmeExcerpt":"Genric Agents **Purpose:** This repository implements **Jobseekers**, a job search conversational agent that analyzes resume information and user queries to provide personalized job recommendations and even apply to roles on the user’s behalf. It supports multiple agent frameworks — **LangChain**, **LangGraph**, and **CrewAI** — and follows a modular architecture that separates concerns across API, agent orchestratio","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# create conda env (recommended)\nconda create -n genric-agents python=3.11 -y\nconda activate genric-agents\n\n# install dependencies\npip install -r requirements.txt"},{"language":"bash","snippet":"export OPENAI_API_KEY=\"sk-...\"\nexport AGENT_FRAMEWORK=langgraph   # or langchain / crewai\nexport OPENAI_MODEL=gpt-4o-mini"},{"language":"bash","snippet":"# option A: run directly\npython main.py\n# option B: uvicorn\nuvicorn main:app --reload --port 8025"},{"language":"bash","snippet":"curl -X POST http://localhost:8025/api/agent/chat \\\n  -H \"Content-Type: application/json\" \\\n  -d '{"},{"language":"bash","snippet":"curl -X POST http://localhost:8025/api/agent/chat \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"sessionId\": \"session-123\",\n    \"prompt\": \"Show me monthly leads by source\",\n    \"payload\": {\n      \"details\": {\"table_name\":\"view\",\"fields\":[]},\n      \"query\": \"monthly leads split by source\"\n    }\n  }'"},{"language":"json","snippet":"{\n  \"status\": true,\n  \"message\": \"\",\n  \"response\": {\n     \"Data\": {...},\n     \"AIMessage\": \"...\",\n     \"ToolMessage\": \"...\",\n     \"Reasoning\": \"...\"\n  }\n}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"Analytics-focused conversational agent framework supporting LangChain, LangGraph, and CrewAI. Generates validated chart/dashlet payloads and query templates from natural language. Genric Agents **Purpose:** This repository implements **Jobseekers**, a job search conversational agent that analyzes resume information and user queries to provide personalized job recommendations and even apply to roles on the user’s behalf. It supports multiple agent frameworks — **LangChain**, **LangGraph**, and **CrewAI** — and follows a modular architecture that separates concerns across API, agent orchestratio","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":387,"uniquenessScore":68,"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":"2026-10-09T05:46:16.565Z","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_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}