Havuz

Python library ve CLI olarak görsel ve videolardaki bazı AI watermark işaretlerini ve provenance metadata'sını bulup kaldırmaya yönelik araçlar sunuyor.

Neden yükseliyor · 186 günlük bir repoda 5685 yıldız ve son 28 günde 150 commit dikkat çekiyor; bu, ilgi ve geliştirme etkinliği için güçlü bir sinyal. Ancak bu artışın nedenini veya kullanım başarısını verilen verilerden doğrulamak mümkün değil; son dönemdeki 3 farklı yazar katkının dar bir grupta yoğunlaşabileceğini gösteriyor.

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

CLI-first hub for agent skills: one npx install, manage in chat, distribute to 70+ agents

The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of

Lossless, local, provable memory for AI agents: every Claude Code session kept on your own computer, word for word, compressed and sealed, a

Local-first, governed documentation for humans and AI agents—mirror Office, PDF, and GitHub sources into linked Markdown knowledge workspace

Find which script, notebook, data, command, or AI agent produced a file — locally, with evidence and honest uncertainty.

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 g

the governed runtime for agent skill workflows, off the leash but on the record

Laravel audit log & change history with real actor attribution (user / job / command / scheduler), cross-model change traces, time machine,

Find and remove AI provenance signals from files you own: hidden Unicode, token watermarks, visible image marks, and C2PA/EXIF/XMP metadata.

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc

AI agents should not make irreversible changes. TraceFold escrows the inverse before an effect lands, or refuses it, and issues receipts any

Git-native AI code provenance: records which AI agent wrote which line, signs each attribution with ed25519, stores it in your git history.

Relational codebase compiler and spec-driven containment engine for AI coding agents. Compiles polyglot repos (Rust, Python, TS, Go, C/C++,

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgve

Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.

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 S

Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a retrieved source - without an LLM call.

Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proof

FinishUP — local-first structured work evidence, deterministic checks, and honest verification receipts.

WAKE.md for AI agents: compile project state so agents stop starting cold.

A Git-native dependency admission controller. Evaluates trust signals on every dependency change and blocks commits or builds when packages

Live audit log of every command, file, and network connection a Claude Code (or any matched) session makes, from the kernel.

Open-source MCP server over a git-backed Obsidian vault. Single-user, self-host. Six tools, hybrid search, provenance/blame, auto-link disco

Sign images and videos with C2PA provenance declaring AI-generated media.