provenance
watermarks-remover
A privacy-first app that strips AI watermarks from content you own.
- 28k
- Python
- MIT
- 4 d ago
remove-ai-watermarks
Remove visible and invisible AI watermarks from images and video, and AI provenance metadata from images, video, and audio. Python library, CLI, and agent skill for SynthID, C2PA, EXIF, IPTC, XMP, and common generative-AI marks. By Victor Kuznetsov.
- 6.5k
- Python
- Apache-2.0
- 5 h ago
scancode-toolkit
:mag: ScanCode detects licenses, copyrights, dependencies by "scanning code" ... to discover and inventory open source and third-party packages used in your code. Sponsored by NLnet, the Google Summer of Code, Azure credits, nexB and other generous sponsors!
- 2.7k
- Python
- 10 d ago
bernstein
Open-source AI agent governance. Write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
- 1.2k
- Python
- Apache-2.0
- 8 h ago
OpenRath
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
- 956
- Python
- BSD-3-Clause
- 8 wk ago
Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
- 722
- Python
- MIT
- 20 h ago
factcircuit
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
- 926
- Python
- MIT
- 8 d ago
provenance-action
Fail CI when dependencies in your lockfile lose npm provenance or trusted publisher status
- 310
- TypeScript
- MIT
- 9 h ago
brain0
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.
- 278
- Rust
- Apache-2.0
- 10 d ago
content-seal
Content Seal is a state-of-the-art framework for invisible, robust watermarking across all modalities audio, image, video, and text. This suite spans the entire generative lifecycle, from training data and inference to generated media.
- 243
- HTML
- MIT
- 2 wk ago
skills-manager
CLI-first hub for agent skills: one npx install, manage in chat, distribute to 70+ agents
- 243
- TypeScript
- MIT
- 2 wk ago
design-harness
Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.
- 236
- Python
- 3 mo ago
construct
Persistent, editable objects for AI agents: researched part by part, honest about what is known, and carried into worlds, film, web, games, CAD and print.
- 168
- Python
- Apache-2.0
- 8 d ago
skill-publish
GitHub Action and CLI to validate, monitor, and publish verifiable skills (SKILL.md) via Registry Broker
- 166
- JavaScript
- 7 mo ago
signet
The seal of approval for agents and skills: a graph-first semantic governance registry with signed, transparency-logged publication trust.
- 132
- TypeScript
- BSD-3-Clause
- 11 h ago
alchemylake-databricks
Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed source (Sample Lakehouse, UC, Genie, or BYO data) into infographics, reports, decks, video briefings, music, and podcasts.
- 118
- Python
- Apache-2.0
- 4 mo ago
agent-custody
Proof of what your AI agents did. Give your agents real power, without losing control of them.
- 113
- TypeScript
- Apache-2.0
- 1 d ago
MirrorArc
Local-first, governed documentation for humans and AI agents—mirror Office, PDF, and GitHub sources into linked Markdown knowledge workspaces.
- 97
- Python
- AGPL-3.0
- 7 wk ago
tejolote
A highly configurable build executor and observer designed to generate signed SLSA provenance attestations about build runs.
- 75
- Go
- Apache-2.0
- 23 h ago
FABULA-LLM-5
A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.
- 82
- TypeScript
- MIT
- 8 wk ago
cairn-memory
Cairn.ink Memory: lightweight cross-session memory for AI agents, with receipts.
- 54
- JavaScript
- Apache-2.0
- 3 d ago
dream-machine
The Dream Machine — a config-driven engine for nightly, cloud-scheduled, evidence-gated repository evolution. Composes @metaharness/flywheel, darwin, and redblue behind a promotion gate that never merges.
- 48
- TypeScript
- MIT
- 2 d ago
isnad
Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines
- 54
- Python
- Apache-2.0
- 4 wk ago
agentic-graphrag
Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have and the decisions they make. Each decision links back to the passages and task events behind it, so agents can look up earlier decisions with their evidence, resume work across sessions.
- 43
- Python
- Apache-2.0
- 9 d ago
watermark-remover
Find and remove AI provenance signals from files you own: hidden Unicode, token watermarks, visible image marks, and C2PA/EXIF/XMP metadata. Zero-dependency Python 3.10+ core; models, GPUs, and system binaries sit behind opt-in adapters.
- 36
- Python
- MIT
- 5 d ago
agent-evidence-vectors
Conformance corpora and reference verifiers for AI-agent and supply-chain evidence formats
- 33
- Python
- Apache-2.0
- 2 d ago
probity
Open tools that check claims about AI agents against evidence you pin: an offline verifier with replayable decisions
- 35
- Python
- Apache-2.0
- 11 h ago
ai-text-watermark
Invisible, key-verifiable watermarks for AI/LLM-generated text — SynthID-Text-style, in Rust + WebAssembly (Node + browser). Live playground included.
- 33
- Rust
- MIT
- 10 d ago
huqan
Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.
- 31
- JavaScript
- Apache-2.0
- 2 d ago
nf-prov
Nextflow plugin to render provenance reports for pipeline runs. Supports standard formats such as BioCompute Object and Workflow Run RO-Crate.
- 31
- Groovy
- Apache-2.0
- 2 wk ago
worldgraph
Privacy-aware environmental digital twin for ambient/RF sensing in Rust — a typed, provenance-tracked graph of rooms, sensors, people & beliefs, geospatially grounded with predictive occupancy (OccWorld). ADR-139.
- 30
- Rust
- Apache-2.0
- 8 d ago
Keystroke Provenance Replay
Replay interactions with keystroke-level provenance
Runs in the browser on Hugging Face
- 0
- mit
- 2 wk ago















