AgentDish directory
provenance
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
|
#126
→ 0
Veracium
A provenance-aware memory layer for AI agents that stores user facts, interaction history, and third-party claims with source tracking and quarantine rules. |
Developer Tools / AI Memory / Agent Infrastructure | 89 | → 0 | 48 days ago | Details |
|
#350
↓ -4
MathKernel
An evidence-aware mathematics runtime for LLMs and a Python/MCP server. It combines exact, symbolic, formal, certified-interval, and numeric computation with typed outputs, trust labels, and provenance tracking. |
Developer Tools / AI/LLM Orchestration | 87 | ↓ -4 | 2 days ago | Details |
|
#532
↑ +2
Provena
Open-source Python library for AI agent context governance with tamper-evident audit trails, provenance validation, freshness checks, and adapter support for common agent stacks. |
Developer Tools / AI Agent Tooling | 86 | ↑ +2 | 50 days ago | Details |
|
#661
↓ -3
Radia
Radia is an agent coordination layer for independently deployed agents, with immutable records, lease-based claims, permissions, and provenance tracking for who acted and what produced each result. |
Developer Tools / AI Agent Infrastructure | 85 | ↓ -3 | 5 days ago | Details |
|
#1034
↓ -6
Neurvance
Neurvance provides CC0-licensed AI training data bundles with document-level provenance, EU AI Act Article 10/Annex IV mapping, and an API for bulk download and RAG retrieval. |
Developer Tools / Code Assistant | 84 | ↓ -6 | 114 days ago | Details |
|
#1091
↓ -3
Astrum HSAM — embedded
A no_std Rust memory engine for on-device LLM agents that uses provenance-aware recall to keep a model’s own output from becoming evidence. |
Developer Tool / AI Memory / Agent Infrastructure | 83 | ↓ -3 | 5 days ago | Details |
|
#1112
↓ -3
Syndicate OS
Self-hosted multi-agent federation for running Hermes agents and OpenClaw minions with a board, tender market, memory layers, and decision provenance. |
Developer Tools / Code Assistant | 83 | ↓ -3 | 19 days ago | Details |
|
#1198
↓ -3
h5i
h5i is an AI-aware Git sidecar that records agent activity, reasoning traces, prompts, model metadata, and review signals in Git refs so teams can hand off work between coding agents and surface PR review briefs. |
Developer Tools / Version Control / AI DevOps | 83 | ↓ -3 | 97 days ago | Details |
|
#1660
↑ +6
Us vs. Them
A CLI/library for line-level provenance in text edited by humans and agents, using version history to estimate which ranges are human-written versus machine-generated. |
Developer Tool / Version control / provenance | 78 | ↑ +6 | 31 days ago | Details |
|
#1947
↑ +1
How Claude marks AI-generated content
Anthropic help article explaining how Claude marks generated text with embedded watermarks and signed provenance metadata, plus what the markings cover, how to detect them, and key limitations. |
Developer Tools / Code Assistant | 72 | ↑ +1 | 29 days ago | Details |