Python SDK

Rethinking Search as Code Generation

Rethinking Search as Code Generation Evolving search from monolithic services to programmable primitives for the era of agent harnesses. Search is a core primitive for AI systems. Frontier models grow more capable by the month, but they still need access to fresh, accurate, and well-curated knowledge from the wider world.

Show HN: TakoVM – Isolated model and tool execution used by enterprises

Run untrusted Python safely. Job queues and Docker isolation built-in. Run AI-generated code in isolated Docker containers with optional gVisor sandboxing.

AI agents get their own phone directory built atop DNS

Flipper Zero Zig Template

A modern, production-ready template for developing Flipper Zero applications using the Zig programming language. This project provides a streamlined build system that integrates Zig with the Flipper Zero SDK, enabling developers to write type-safe, memory-safe applications for the Flipper Zero platform. This template bridges Zig's powerful build system and language features with the Flipper Zero firmware development kit.

Universal Memory Protocol – a shared format for agent memory

Universal Memory Protocol The third interoperability layer Section titled “The third interoperability layer”Agents can already call tools (MCP) and talk to each other (A2A). What they can’t do is carry memory across sessions, agents, and vendors.

Pyro Caml Continuous Profiler for OCaml

The core SAST engine of Semgrep is written in OCaml. There are a lot of good technical and historical reasons for this that I’ll leave for another time. An important consequence of using a language with a (relatively) small ecosystem like OCaml is that there aren’t a lot of libraries for things like observability, which are critical for running industrial software like Semgrep on hundreds of thousands of code repositories, and keeping it both reliable and performant.

Show HN: Solving complex optimization problems with Google OR-Tools in browser

Solve complex optimization models from TypeScript with Google OR-Tools running as multithreaded WebAssembly. Used in PragmaPlanner Run the local test site: npm install npm run dev Install from npm: npm install or-tools-wasm Import the solver API you need from its subpath: import { CpSat } from 'or-tools-wasm/cp-sat'; Public solver APIs live under solver-scoped subpaths: import { CpModel, CpSolver } from 'or-tools-wasm/cp-sat'; import { RoutingIndexManager, RoutingModel } from...

ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer

Announce Type: new Abstract: The rapid proliferation of Agent Development Kits (ADKs), SDK-level frameworks for building LLM-powered autonomous agents, has outpaced any empirical understanding of how framework choice affects agent performance. We propose \textbf{LLM-as-a-Developer}, a methodology that replaces human developers with an LLM coding agent that learns each framework's API from documentation, writes agent code, and iteratively repairs it through a validate-and-feedback loop until...

Launch HN: Intuned (YC S22) – Build and run reliable browser automations as code

Hey HN, we're Faisal and Ahmad from Intuned (https://intunedhq.com). We’re building a platform for building, deploying, and maintaining browser automations. Customers primarily use the Intuned AI agent to automate websites that don't expose APIs.

Show HN: Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)

Local-first AI memory layer for any LLM. Persistent knowledge graph, entity extraction, semantic retrieval — no cloud required. Most LLMs forget everything the moment a conversation ends.