#provenance

Security-First Agentic IDE Coding Harness

Open-source loop engineering for auditable business briefings: claims, evidence, gates, findings, repairs, and human review.

Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall

Attack taxonomy, toolkit & defenses for persistent-memory poisoning of LLM agents. Author: Krishita Sanjay Choksi.

Verifiable audit substrate for AI agents — EU AI Act Article 12 ready. Apache 2.0.

Governed operating loops and portable capability Capsules for persistent AI agents

Cryptographic provenance for AI agents on the live web. Ed25519-signed, hash-chained evidence for every Bright Data fetch. EU AI Act Article 12 compliant. MIT.

Give your AI a second brain. Altretta connects your local, encrypted knowledge vault to 70+ AI agents with query-first, cited retrieval and signed provenance.

FOSS-first, local-first capability and evidence layer for AI agents. Local MCP server and CLI for safe, cited web access: SSRF-hardened fetch, provenance-tracked research packets, and security decided outside the model.

Verified, git-aware memory for autonomous software agents—tracking what worked, what failed, what is currently true, and the evidence that proved it.

An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a poisoned input contaminated. Built on substrate.

Knowledge in common. Governed, plain-file memory for humans and their AI agents: you own the corpus, agents propose, a deterministic gate decides, provenance travels with every record. Local-first, no accounts, no telemetry.

NOA — the Agent Action Receipt. Open governance layer for AI agents: gate risky actions before they run, emit a tamper-evident receipt anyone can verify offline. Early access · Apache-2.0.

MYND Knowledge Paleontology — Knowledge origin and lineage tracking for AI systems. The fossil record of what AI knows and where it came from.

GitHub Action + CLI for replayable CI/PR/release gate decisions - zero-config Self-Test turning checks, scanners, and AI-agent signals into deterministic, tamper-evident PASS/WARN/BLOCK records. Read-only, zero dependencies, Apache-2.0.

Document parsing that never loses provenance: Markdown + JSON output where every block knows its source page, section, and location.