Stdio JSON-RPC server plugin for out-of-process DeepSeek Harness SDK clients

Deep Agents - a library for building controllable AI agents with LangGraph

React is a JavaScript library for building user interfaces.

Client command surface: global directory cache, '/' source, three command UI kinds, popupSelect registry

_This package is **experimental**._

Local-process sandbox provider for TanStack AI — runs the agent directly on the host through the uniform SandboxHandle (no isolation; trusted/dev use).

Input trigger pipeline: '/' and '@' detection, candidate menu, pick routing to registered sources

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench code-repair — conformant GLM->Opus empty-patch cascade resolves 51.3% Lite (n=300) and 55.6% Verified (278/500, Wilson 95% CI [51.2, 59.9], official swebench gold eval, no gold

`HarnessV1` adapter backed by [`@openai/codex-sdk`](https://www.npmjs.com/package/@openai/codex-sdk), which drives the `codex` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSocket on a sandbox-proxied l

TypeScript SDK for Strands Agents framework

The dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)

`HarnessV1` adapter backed by [`@anthropic-ai/claude-agent-sdk`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk), which drives the `claude` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSo

The OpenCode harness connects `HarnessAgent` to OpenCode through a sandboxed bridge.

`HarnessV1` adapter backed by [`@earendil-works/pi-coding-agent`](https://www.npmjs.com/package/@earendil-works/pi-coding-agent). Pi runs in the host Node.js process and uses the sandbox as a remote filesystem + shell — no bridge process is installed insi

Reusable multi-agent harness for AI-assisted development: personas, skills, operating rules, model routing, and QA gates. Deploy into any project with `npx @dombaras/agent-harness init`.

Local-subprocess implementation of the DeepSeek Harness subprocess seam

Prebuilt system primitives: a Linux Landlock launcher and asynchronous POSIX flock through stable Node-API

Nuxt module that adds a complete AI chat interface to your app. Server-side chat behavior is delegated to the dedicated Chat API; the Nuxt module owns the UI, auth bridge, and local proxy routes.

Local process-sandbox backends for the DeepSeek Harness sandbox seam: bwrap, the npm-distributed landlock-run launcher, macOS Seatbelt, or the Windows ACL restricted-token runner — functionally probed, fail-closed