agience-core
Agience Core is an open, extensible runtime for agentic AI centered on shared, typed, versioned “artifacts” with provenance and human-in-the-loop workflows. It is positioned as both an MCP server (exposing tools) and an MCP client (consuming vendor MCP servers), and emphasizes capability-based access via scoped API keys and delegations tracked by authority/provenance.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Security claims are architectural (scoped API keys, identity from token, delegated operations tracked by authority). The provided content does not specify TLS enforcement, secret storage practices, or dependency/security maintenance details, so security scores beyond auth/scoping are estimates. License is AGPL-3.0-only; ensure operational practices support secure deployment and secret management.
⚡ Reliability
Best When
You need an auditable shared-state runtime where agents and humans operate on the same typed artifacts, with MCP-based extensibility and governance/provenance modeled as first-class architecture.
Avoid When
You need a lightweight, minimal integration without standing up an MCP server/runtime, or you cannot accept AGPL obligations for network deployment/modification.
Use Cases
- • Shared knowledge/state layer for AI agents and humans (curation + automated reasoning)
- • Auditable decision/knowledge workflows with explicit provenance and authority
- • Building agent tool ecosystems via MCP (standalone services / content-type handlers)
- • Human-in-the-loop commit/approval flows for knowledge transformations
- • Semantic retrieval and knowledge graph/search use with OpenSearch (per repo topics)
Not For
- • Drop-in chat-only chatbot UI solutions without a shared state/provenance model
- • A fully managed hosted SaaS with guaranteed uptime/SLA and proprietary licensing expectations
- • Use cases requiring no governance/audit trail or simple stateless APIs
- • Environments that cannot comply with AGPL-3.0 requirements for network-accessible deployments
Interface
Authentication
README indicates scoped API keys and delegation records, but does not provide concrete auth flow details, header formats, or scope naming conventions in the provided content.
Pricing
No hosted pricing information in provided content; licensing indicates AGPL-3.0-only with commercial licensing for proprietary/closed-source use.
Agent Metadata
Known Gotchas
- ⚠ Provided README does not include concrete MCP server tool schemas, transport details, or error-handling conventions; agents may need to infer behaviors until full docs are available.
- ⚠ Idempotency/retry guidance is not documented in the provided content; agent runtimes should implement cautious retry logic for any state-changing operations.
- ⚠ Because it is positioned as a runtime with artifacts/provenance and human approval gates, agent flows may require explicit commit/approval steps to avoid unexpected “denied until commit” behavior.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for agience-core.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.