Havuz

Evidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. 讓 AI agent 做研究時

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

A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.

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

Minimal Ed25519-signed activity receipts for verifiable AI agents — self-attested, offline-verifiable, no blockchain.

Evidence validation and policy engine for AI-assisted biological curation

Version control for AI agent memory. Commit, branch, merge, blame and time-travel what your agents know.

Cairn.ink Memory: lightweight cross-session memory for AI agents, with receipts.

Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, prov

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

Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MC

Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have

铃音的记忆写入协议 - an informatics protocol: fragmented, cue-based, symbolic, highly compressed information for AI agents; usable for memory writing

Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.

Invisible, key-verifiable watermarks for AI/LLM-generated text — SynthID-Text-style, in Rust + WebAssembly (Node + browser). Live playground

Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.

The Dream Machine — a config-driven engine for nightly, cloud-scheduled, evidence-gated repository evolution. Composes @metaharness/flywheel

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

Test what AI watermark and provenance evidence exists, whether it verifies, and what survives publishing.

watermarks-remover, kullanıcının sahip olduğu içeriklerdeki görünür olmayan metin işaretlerini ve dosya provenance metadata’sını temizlemek için Python service ve agent skill sunuyor.

Neden yükseliyor · 47 günde 22.900 yıldız ve son 28 günde 64 commit ile 18 farklı yazar kayda değer ilgi ve geliştirme temposu gösteriyor. Yükselişin kesin nedenini verilen verilerden çıkarmak mümkün değil; AI provenance ve gizlilik konularına dönük ilgi olası etkenler.

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

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

A verifiable local memory architecture for long-running AI agents

a DSL for automated deterministic rules. Built for AI agents and quantitative Trading systems.

Provena : Context governance for agentic AI — tamper-evident audit trails, provenance validation, EU AI Act compliance. 6 framework adapters

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai

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

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works w

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

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed

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

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

Governed knowledge bases that humans and AI agents write together: append-only, bitemporal, conflict-aware.

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

Privacy-aware environmental digital twin for ambient/RF sensing in Rust — a typed, provenance-tracked graph of rooms, sensors, people & beli

Decision provenance and data-flow tracking for coding agents: computes what changed in your code and data, records why it changed, and surfa

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

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

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

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

Local-first knowledge graph that gives your AI assistant durable, provenance-backed memory across sessions and agents/LLMs

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self

Epistemic settlement memory. Shared, external and verifiable.

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

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

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

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