provenance
20 servers · 1,145★ total
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
The operating system that AI workflows trust. Structure messy inputs. Establish identity. Track provenance. Build the durable data layer your AI workflows need to be trusted, reusable, and auditable.
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
Local pre-flight linter and architecture gate for AI agents. Uses tree-sitter, Stack Graphs, and Datalog to mechanically block structural drift, layering bypasses, and scope creep on virtual ASTs before code changes land.
TRACE protocol for auditing decision-provenance in AI-assisted scientific workflows
Governed state engine for AI agents: typed, executable knowledge artifacts with a code-like lifecycle
Agent memory that needs no API key, no LLM, and no embedding provider. One command on Bun and it is serving MCP over stdio against a local SQLite store. Drop-in for the MCP reference memory server. Every memory keeps its source, who may read it, and the evidence that contradicts it.
Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable by anyone.
Memory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.
Turns any text stream into a dated history of how its subject changed. Point it at your Claude Code / OpenCode sessions to track how you think and work, or at market news, research notes, or any corpus to track how that changed — raw records to observations to bi-temporal facets to narrative, with provenance, served over MCP. Single pure-Go binary.
The provenance-first personal graph engine behind Wend. A typed graph of people, organizations and events where every fact carries a source, every AI write is a human-confirmed proposal, and any MCP-capable agent can plug in.
Chat with your electronic lab notebooks
Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.
Contract-first orchestration for long-running coding agents: scoped work records, local dispatch, review evidence, and enforcement provenance.
Neurosymbolic Forge — an MCP server that turns concepts into verifiable, traceable formulas via deterministic symbolic derivation with provenance. 89 tools, 10-gate verification harness.
A tamper-evident, local-first audit trail for AI-agent work — an MCP server with typed tools behind workflow gates and a signed, hash-chained log anyone can verify without a secret.
BioMed MCP over AlphaFold DB + 8 public sources, with SQLite knowledge graph, offline mode, and explicit clinical-use limits.
Research intake that reaches the hard places: web, video, papers, scanned PDFs, browser, OCR, and audio into structured research packets. DOM extraction and change tracking built in; provenance rides along on every item.
Python and MCP tools for testing falsifiable claims and recording MATCH, DRIFT, or UNVERIFIABLE outcomes against supplied evidence.