{"id":"a35232d5-37d0-4a0a-8a92-9f2d1fbcd60f","entityType":"agent","slug":"crewai-vrushalishrianantsavant23-cmyk-axiom-agent","name":"Axiom-agent","canonicalUrl":"https://www.xpersona.co/agent/crewai-vrushalishrianantsavant23-cmyk-axiom-agent","canonicalPath":"/agent/crewai-vrushalishrianantsavant23-cmyk-axiom-agent","generatedAt":"2026-10-10T09:00:34.221Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T15:16:43.703Z","emptyReason":null},"description":"Self-verifying agentic AI system for claim/document fact-checking — combines LangGraph orchestration, CrewAI multi-agent verification, semantic entropy-based uncertainty quantification, and safety guardrails to reduce hallucination and provide transparent, confidence-scored answers. Axiom-Agent **A self-verifying agentic AI system for claim and document fact-checking** Axiom-Agent goes beyond typical RAG chatbots by combining multi-agent verification, research-grounded uncertainty quantification, and safety guardrails to produce grounded, confidence-scored, and transparent answers — rather than confidently hallucinating. Why this project Most GenAI assistants report confidence as a simple self-r","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/vrushalishrianantsavant23-cmyk/Axiom-agent","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/vrushalishrianantsavant23-cmyk/Axiom-agent","kind":"source"}],"safetyScore":66,"overallRank":21.6,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Self-verifying agentic AI system for claim/document fact-checking — combines LangGraph orchestration, CrewAI multi-agent verification, semantic entropy-based un"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T15:16:43.703Z","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":"2026-10-09T15:16:43.703Z","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":"2026-10-09T15:16:43.702Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T15:16:43.703Z","lastCrawledAt":"2026-10-09T15:16:43.702Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T15:16:43.702Z","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-vrushalishrianantsavant23-cmyk-axiom-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-agent/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-agent/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-agent/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-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":"2026-10-10T09:00:34.220Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-agent/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-vrushalishrianantsavant23-cmyk-axiom-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":"2026-10-09T15:16:43.703Z","emptyReason":null},"readme":"# Axiom-Agent\n\n**A self-verifying agentic AI system for claim and document fact-checking**\n\nAxiom-Agent goes beyond typical RAG chatbots by combining multi-agent verification, research-grounded uncertainty quantification, and safety guardrails to produce grounded, confidence-scored, and transparent answers — rather than confidently hallucinating.\n\n## Why this project\n\nMost GenAI assistants report confidence as a simple self-rated number from the LLM itself, which is often overconfident and poorly calibrated. Axiom-Agent instead measures uncertainty statistically using **semantic entropy** (based on Farquhar et al., *Nature*, 2024) — sampling multiple responses and measuring how consistent the model actually is with itself, rather than trusting what it says about itself.\n\nThis directly addresses several open challenges discussed in current agentic AI / LLM research:\n- Hallucination detection happening after generation rather than being addressed during it\n- Lack of transparency in how agents arrive at conclusions\n- Overconfidence and poor uncertainty calibration\n- Vulnerability to adversarial / prompt-injection inputs\n\n## Architecture\n\n```\nUser Query\n   │\n   ▼\n[Moderation Node] — blocks harmful/illegal/unethical requests\n   │\n   ▼\n[Semantic Entropy Node] — samples 5 responses, clusters by meaning, computes uncertainty\n   │\n   ▼\n[Retriever Node] — fetches supporting evidence from ChromaDB\n   │\n   ▼\n[CrewAI Verification Crew]\n   ├── Fact-Checker Agent\n   ├── Skeptic Agent\n   └── Judge Agent (neutral, multi-perspective on contested topics)\n   │\n   ▼\n[Output Safety Node] — validates against schema, falls back to \"insufficient evidence\" if needed\n   │\n   ▼\nFinal structured response (answer + confidence + sources + full reasoning trace)\n```\n\n## Tech Stack\n\n- **Backend:** FastAPI\n- **LLM:** Google Gemini (gemini-2.0-flash)\n- **Agent orchestration:** LangGraph\n- **Multi-agent verification:** CrewAI\n- **Vector store:** ChromaDB + sentence-transformers\n- **Frontend:** Streamlit\n- **Validation:** Pydantic\n\n## Features\n\n- 🧠 Semantic entropy-based uncertainty quantification (not simple LLM self-rating)\n- 🔍 Multi-agent cross-verification (fact-checker, skeptic, judge)\n- 🛡️ Input moderation + output safety guardrails\n- ⚖️ Neutrality enforcement on contested/subjective topics\n- 📜 Full reasoning trace logging for transparency and reproducibility\n- ⚔️ Live adversarial testing endpoint to demonstrate guardrail robustness\n\n## Setup\n\n```bash\npip install -r requirements.txt\ncp .env.example .env\n# add your GEMINI_API_KEY to .env\n\n# run both servers\nfuser -k 8000/tcp 2>/dev/null; fuser -k 8501/tcp 2>/dev/null\nuvicorn app.main:app --host 0.0.0.0 --port 8000 &\nstreamlit run streamlit_app.py --server.port 8501\n```\n\nOr simply:\n```bash\nchmod +x run.sh\n./run.sh\n```\n\nOpen the Streamlit UI (port 8501) or the FastAPI docs at `/docs` (port 8000).\n\n## API Endpoints\n\n| Method | Endpoint | Description |\n|--------|----------|-------------|\n| GET | `/health` | Health check |\n| POST | `/ingest` | Upload and index a document |\n| POST | `/verify` | Verify a claim, returns full structured response |\n| GET | `/trajectory/{query_id}` | Retrieve past reasoning trace |\n| POST | `/adversarial-test` | Test guardrails against adversarial input |\n\n## Honest scope\n\nThis project **reduces** hallucination and improves transparency — it does not fully **solve** hallucination, which remains an open research problem. Confidence scores are a statistically-grounded signal, not a rigorously calibrated probability. Guardrails handle common adversarial patterns; they are not enterprise-grade adversarial defense.\n\n## Author\n\nBuilt as a final-year academic project with a placement-portfolio focus.\n","readmeExcerpt":"Axiom-Agent **A self-verifying agentic AI system for claim and document fact-checking** Axiom-Agent goes beyond typical RAG chatbots by combining multi-agent verification, research-grounded uncertainty quantification, and safety guardrails to produce grounded, confidence-scored, and transparent answers — rather than confidently hallucinating. Why this project Most GenAI assistants report confidence as a simple self-r","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"User Query\n   │\n   ▼\n[Moderation Node] — blocks harmful/illegal/unethical requests\n   │\n   ▼\n[Semantic Entropy Node] — samples 5 responses, clusters by meaning, computes uncertainty\n   │\n   ▼\n[Retriever Node] — fetches supporting evidence from ChromaDB\n   │\n   ▼\n[CrewAI Verification Crew]\n   ├── Fact-Checker Agent\n   ├── Skeptic Agent\n   └── Judge Agent (neutral, multi-perspective on contested topics)\n   │\n   ▼\n[Output Safety Node] — validates against schema, falls back to \"insufficient evidence\" if needed\n   │\n   ▼\nFinal structured response (answer + confidence + sources + full reasoning trace)"},{"language":"bash","snippet":"pip install -r requirements.txt\ncp .env.example .env\n# add your GEMINI_API_KEY to .env\n\n# run both servers\nfuser -k 8000/tcp 2>/dev/null; fuser -k 8501/tcp 2>/dev/null\nuvicorn app.main:app --host 0.0.0.0 --port 8000 &\nstreamlit run streamlit_app.py --server.port 8501"},{"language":"bash","snippet":"chmod +x run.sh\n./run.sh"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"Self-verifying agentic AI system for claim/document fact-checking — combines LangGraph orchestration, CrewAI multi-agent verification, semantic entropy-based uncertainty quantification, and safety guardrails to reduce hallucination and provide transparent, confidence-scored answers. Axiom-Agent **A self-verifying agentic AI system for claim and document fact-checking** Axiom-Agent goes beyond typical RAG chatbots by combining multi-agent verification, research-grounded uncertainty quantification, and safety guardrails to produce grounded, confidence-scored, and transparent answers — rather than confidently hallucinating. Why this project Most GenAI assistants report confidence as a simple self-r","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":392,"uniquenessScore":66,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T15:16:43.703Z","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":"2026-10-09T15:16:43.703Z","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":"2026-10-10T09:00:34.221Z","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"}]}}}