agentlib — blog

Voice in, vision out, device automation: building a pocket assistant with agentlib

Tue, 09 Jun 2026 00:00:00 GMT

Wire voice input, vision-based screen understanding, accessibility-driven app automation, and on-device routing together. The pocket-assistant pattern in agentlib.

MCP on mobile: HTTP and WebSocket transports for Model Context Protocol servers

Sat, 06 Jun 2026 00:00:00 GMT

agentlib speaks Model Context Protocol over both HTTP and WebSocket. MCP tools surface as /bin/mcp.. CLIs, ready for Sh pipelines. Notifications stream live.

Suspend, resume, and push-resume: agents that survive the OS lifecycle

Thu, 04 Jun 2026 00:00:00 GMT

iOS backgrounds apps. Android kills processes under memory pressure. agentlib's Runner state is serialisable, lifecycle hooks fire on every transition, and push notifications can wake the agent.

21 hooks: the most fine-grained agent loop in any SDK

Tue, 02 Jun 2026 00:00:00 GMT

agentlib has more interception points than any other agent SDK. PreToolUse, PostToolUse, OnSuspend, OnLowBattery, OnNetworkChange — guardrails without prompt hacking.

Snapshots, revert, fork: time-travel debugging for mobile AI agents

Sat, 30 May 2026 00:00:00 GMT

agentlib's snapshot API is public, content-addressed, and SQLite-backed. snapshot(), revert(), fork() — and an auto-snapshot before any highImpact tool call so users can always undo.

Subagents at scale: parallel and background dispatch on mobile

Thu, 28 May 2026 00:00:00 GMT

agentlib's subagents run sync, in parallel, or in the background — each with its own context window. Research + draft simultaneously; index in the background; survive backgrounding.

Progressive-disclosure skills: 30 skills in 600 tokens

Mon, 25 May 2026 00:00:00 GMT

Skills are markdown bundles that load lazily. The orchestrator sees only name + description until invocation, so a 30-skill catalog costs ~600 tokens instead of 12 K.

agentlib vs Claude SDK vs OpenAI Agents SDK vs Mastra vs LangChain: which to use

Fri, 22 May 2026 00:00:00 GMT

A practical decision tree for picking an agent SDK in 2026. The short answer: pick by where your agent runs — server, edge, or device. Here's the long answer.

agentlib 1.1.0: MCP WebSocket, SQLite snapshots, in-loop handoffs

Fri, 22 May 2026 00:00:00 GMT

Three big additions in 1.1.0 — full-duplex MCP via WebSocket, a content-addressed SQLite snapshot store, and OpenAI-style in-loop handoffs between agents.

CLI-first agent design: why agentlib's Sh mini-shell matters

Mon, 18 May 2026 00:00:00 GMT

Frontier LLMs are most fluent in Unix idioms — Read/Grep/Edit and cmd | jq | xargs. agentlib's Sh gives the model that surface inside a sandbox. Here's why it matters.

On-device AI agents in Flutter: Foundation Models, Gemini Nano, llama.cpp

Fri, 15 May 2026 00:00:00 GMT

agentlib runs agents on the phone. Four on-device providers — Apple Foundation Models, Gemini Nano, MediaPipe, Fllama — behind one ModelRoute.preferOnDevice([...]) call.

Why agentlib is the only mobile-native AI agent SDK

Tue, 12 May 2026 00:00:00 GMT

Every other agent SDK assumes a Node or Python runtime that doesn't fit inside an iOS app sandbox. agentlib is pure Dart, with native bridges for Apple Foundation Models and Gemini Nano.