81,580 packages matching “multi-turn”
anyclaude-sdk
v0.15.19 · 9 days ago
Standalone, browser-compatible SDK providing Claude Code agent capabilities (tools, tool loop, multi-turn, MCP, sub-agents, sessions) against any OpenAI/Anthropic-compatible LLM endpoint. Runs in the browser (WebContainer), Node, and Bun — no backend requ
No known vulnerabilities
@ggui-ai/ui-gen
v0.9.0 · 3 days ago
UI generation harness for ggui — the LLM system prompt, multi-turn coding loop, and evaluation engine that turn a DataContract into a React component. Implements the UiGenerator contract from @ggui-ai/mcp-server-core; consumed by @ggui-ai/mcp-server.
No known vulnerabilities
n8n-nodes-kimi-ai
v0.1.2 · 2 months ago
Kimi AI (Moonshot AI) n8n custom node for chat completions, multi-turn conversations, streaming, and memory management.
No known vulnerabilities
expo-apple-llm
v0.2.0 · 3 months ago
Expo module for Apple's on-device LLM (Foundation Models, iOS 26+). One-shot generation and multi-turn LanguageModelSession, no network or API key.
No known vulnerabilities
@cola_runner/gemini-notebook-cli
v0.2.1 · 18 days ago
Agent-first unofficial Gemini Notebook client for Node.js — JSON CLI, citations, multi-turn chat, all studio artifacts, research & notes
No known vulnerabilities
pi-grok-sdk
v0.2.1 · 1 month ago
Use Grok Build inside pi via the local xAI agent CLI — real agent tools, multi-turn ACP sessions, and native thinking/text streaming.
No known vulnerabilities
@ai37/a2a-redis-task-store
v0.1.0 · 1 month ago
Redis-backed A2A TaskStore for @a2a-js/sdk, built on ioredis: durable Task snapshots for multi-turn/HITL, resubscribe and replay
No known vulnerabilities
@almyty/chat
v1.2.0 · 24 days ago
Chat with your almyty agents in an interactive terminal REPL — multi-turn and streaming, with tool calls and autonomous runs.
No known vulnerabilities
scuttlerun
v0.3.0 · 2 months ago
Multi-turn Claude session driver
No known vulnerabilities
@zvada/agent-server
v0.3.0 · 6 hours ago
Harness-agnostic agent execution engine: run Claude Code, Codex (SDK/CLI + app-server), and any ACP agent behind one interface with a normalized event stream, multi-turn sessions, and resume. Root export is the wire contract; /core, /server, /client are t
No known vulnerabilities
@aster110/cc-core
v0.1.0 · 4 months ago
Claude Code SDK adapter core - session pool, Agent Teams, multi-turn
No known vulnerabilities
@dileeppandiya/skilleval
v0.3.0 · 1 month ago
Measure whether Claude SKILL.md files improve outputs — blind A/B testing, deterministic assertions, multi-turn tasks, skill comparison, run history, and CI gating in under 2 minutes
No known vulnerabilities
@syntaxsmith/rosetta
v0.3.2 · 15 days ago
Programmatic access to ChatGPT Pro by translating between the auth-holder Chrome page and a Node API. Hijacks /backend-api/f/conversation via CDP Fetch.requestPaused, follows the WS second leg for Pro CoT, returns aggregated text + supports multi-turn / r
No known vulnerabilities
a2a-opencode
v1.6.1 · 2 months ago
A2A (Agent-to-Agent) protocol wrapper for OpenCode. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports any agent persona, MCP tool servers, SSE streaming with polling fallback, context building, and multi-turn conversations.
No known vulnerabilities
@vocmarket/voc-skill
v0.3.32 · 17 days ago
Claude Code VOC intelligence skills for Xiaohongshu and Douyin trend reports, live social VOC collection, Fmode image analysis, single-issue deep dives, boss/operator action plans, and multi-turn memory.
No known vulnerabilities
@heimoshuiyu/opencode-goal-plugin
v1.0.0 · 2 months ago
OpenCode plugin that enables autonomous goal-driven agent mode with multi-turn continuation, independent completion verification, and interrupt auto-pause
No known vulnerabilities
agy-bridge
v0.4.1 · 1 month ago
MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, and multi-turn session continuity.
No known vulnerabilities
@rbrowton/ai-client
v1.8.0 · 12 days ago
Shared Anthropic Claude API client with prompt caching, retry, streaming, structured output, multi-turn completion, multi-tool selection, partial-object streaming, pluggable validation, effort control, error hooks, bounded fan-out (concurrency + call-ceil
No known vulnerabilities
@thiagorufino/mcp-hub
v1.0.9 · 3 months ago
MCP Hub is a local web UI for testing LLMs and MCP servers. Connect providers, inspect tool calls, and run multi-turn chats in one place.
No known vulnerabilities
@estebanforge/pi-ask-codex
v1.0.3 · 3 days ago
Pi tool that delegates a self-contained sub-task to OpenAI's Codex CLI via `codex exec --json`. Streams structured events as partial output, returns the final agent message. Configurable default model + reasoning effort, with multi-turn session continuity
No known vulnerabilities