InfoQ Chinese published an edited transcript of a MAD Podcast conversation between Carnegie Mellon professor Andy Pavlo, now vice president of database research at ClickHouse, and host Matt Turck on how AI agents are reshaping database work. Pavlo argues that agents wiping production databases is an old problem resurfacing — permissioning and control mechanisms have existed for decades — and recommends isolating agents with restricted permissions and branch-based sandboxes rather than approving every action by hand. He also offers rough figures: off-the-shelf text-to-SQL tools reach about 60% accuracy, LLM-based database tuning gets roughly 80-85% of the way, and more than 60% of open-source database systems now show agent-authored commits in his dbdb.io tracking.
The project README describes PentAGI as an open-source, self-hosted multi-agent system for autonomous penetration testing, developed by VXControl, a security engineering company based in Dubai. It says a user describes a target and goal in plain language; specialized AI agents plan the work and run 20+ professional tools such as nmap, Metasploit and sqlmap inside an isolated Docker sandbox, remember what they learned and return a report. The README also says results and successful approaches are stored in PostgreSQL with pgvector, with an optional Neo4j-based Graphiti knowledge graph, and that the system supports 10+ cloud LLM providers, an OpenAI-compatible gateway and local models through Ollama or vLLM. These are the project's own claims.
Mastra introduced Trace Queries, letting users of the Mastra platform and local Studio filter and find traces by fields such as time, primitive name, agent or workflow ID, status, score and feedback. The company says the same queries can be built through the CLI ([email protected] or later), the Mastra Client SDK (@mastra/[email protected] or later) and HTTP observability endpoints. Each query covers a time range of up to 31 days, combines up to 100 conditions and allows up to 8 filters on trace internals such as spans, scores and feedback; the feature works on the Mastra platform and on self-hosted projects whose observability storage uses DuckDB, PostgreSQL or ClickHouse, and existing history can be brought in via trace imports.
Apple researchers published a paper describing Minions, an internal "virtual GPU cloud" that aggregates idle Apple Silicon Macs across the network to run machine learning inference. A Minion Server splits submitted jobs into subtasks stored in PostgreSQL, a Minion Executor on each Mac pulls subtasks over REST APIs and runs them on the local GPU with inputs and outputs in Amazon S3, and a Minion Watchdog requeues unfinished work when a machine sleeps, goes offline, powers off or its user stops the executor, using five-minute heartbeats. The paper says Minions only handles inference — embeddings with Hugging Face transformer models and text generation through Ollama installed on each Mac — and Apple reports that some jobs that once faced 10-plus-hour centralized GPU queues could start within minutes, figures that come from Apple's own testing and leave cross-team data confidentiality as an open concern.
Kangaroo Database Tool version 9.9.1 is now available. The AI-driven database client supports MariaDB, MongoDB, MySQL, Oracle, PostgreSQL, Redis, SQLite and SQL Server, along with table creation, queries, modeling, synchronization, and data import/export across Windows, macOS and Linux.
Postquel launched on Product Hunt, described as a free native Postgres app for the Mac that works with your own AI agents. The listing offers only that one-line description, with no details on supported models, how agents connect, or the app's full feature set.
What problem it solves
Organizations need to move and continuously replicate data from transactional databases, event streams, and object storage into open lakehouse formats without depending on proprietary ingestion stacks. OLake Go addresses this with replication workflows, CDC, schema handling, and deployment options that avoid separate Spark, Flink, Kafka, or Debezium infrastructure.
Key featu…
What problem it solves
Teams and individuals need a straightforward way to host and manage their own Git service. Self-hosting requires code hosting, collaboration tools, authentication, integrations, database configuration, and deployment options in one extensible system.
Key features
Code hosting and repository browsing — Host repositories over SSH and HTTP(S), with deploy keys and LFS, and brow…
What problem it solves
Organizations need a distributed storage layer that can serve objects, files, tables, and vectors while keeping administration and horizontal expansion straightforward. SeaweedFS addresses this by providing these capabilities on shared storage and allowing capacity to grow by adding volume servers.
Key features
Unified distributed storage — A single cluster exposes S3 object…
What problem it solves
Organizations need to manage newsletters and mailing lists without relying on a hosted service. listmonk addresses this with a self-contained application that uses PostgreSQL for persistent data and can be deployed as a single binary.
Key features
Self-hosted deployment — Run the application on infrastructure you control, using either Docker Compose or the packaged binary.
S…
What problem it solves
Team conversations can become difficult to follow when discussion mixes live chat with longer-running topics. Zulip organizes messages around topics so teams can structure conversations and support both real-time and asynchronous collaboration.
Key features
Topic-based conversation organization — Messages are organized around topics, helping teams separate discussions and fo…
What problem it solves
Fintech applications need a reliable system of record for wallets, payouts, marketplaces, billing, and agent-initiated payments. They also need exact monetary arithmetic, enforceable spending controls, and evidence that the recorded history has not been altered.
Key features
Exact double-entry accounting — Records transfers, payouts, billing activity, reservations, and refun…
What problem it solves
Managing several Xianyu seller accounts requires coordinating account status, credentials, messages, products, orders, inventory, and delivery workflows. The project brings these activities into one self-hosted console and supports rules for responses, order handling, and automated delivery.
Key features
Multi-account and messaging management — Run and monitor multiple accou…
What problem it solves
Vaultwarden provides an alternative server implementation of the Bitwarden Client API, written in Rust and compatible with official Bitwarden clients. It is intended for self-hosted deployment where running the official resource-heavy service might not be ideal.
Key features
Compatible Bitwarden Client API — The server implements the Bitwarden Client API and is compatible wi…
What problem it solves
Building, deploying, and managing AI agents requires integrating agent behavior, runtime configuration, tools, models, sessions, and observability. The project addresses this with a declarative Kubernetes-based framework that supports multiple runtimes, model providers, and MCP tools.
Key features
Declarative Agent Management — Agents are Kubernetes custom resources that com…
What problem it solves
Call centers need to handle incoming calls automatically while still giving people a clear path to take over when assistance is required. They also need to preserve the conversation context and call history across AI answers, queue transfers, and agent handling.
Key features
AI-answered calls — Calls arrive through FreeSWITCH and are answered by a realtime voice model over a…
What problem it solves
Leaked credentials can be difficult to identify and assess because they may be stored across repositories, chats, wikis, logs, filesystems, and other systems. Finding a credential pattern alone does not establish whether it is active, so the project combines discovery, classification, validation, and analysis.
Key features
Broad secret discovery — Scan sources including Git …
What problem it solves
Keeping personal finances organized requires recording transactions, bringing in data from multiple sources, and finding relevant bills across that history. Users also need ways to understand spending patterns and financial trends while retaining control over where their financial data is stored.
Key features
Self-Hosted Personal Finance — Run the application on infrastructu…
What problem it solves
AI agents need controlled access to browsers, files, and tools while people retain visibility and control over their actions. OpenBot addresses this with isolated Bot computers, policy evaluation, audit records, and human takeover for sensitive steps.
Key features
Isolated computers for every Bot — Each Bot can receive a dedicated container with its own Chromium instance, br…
What problem it solves
Professionals and teams need control over their email and related productivity tools. The project provides custom-domain email, calendar, drive, booking, and built-in AI agents in a self-hosted application.
Key features
Custom-domain email — Create personal or shared mailboxes on a custom domain and send and receive mail through supported providers. Incoming mail can be stor…
What problem it solves
Extracting business information from Google Maps requires collecting details such as contact information, websites, reviews, ratings, and coordinates for each place. The project addresses this workflow by providing command-line, browser, API, and self-hosted interfaces for collecting and exporting those records.
Key features
Multiple interfaces — Choose a command-line workfl…