mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Maxim
13d9d65e01
`createExpenseHarnessStream` now selects its adapter from an `engine` option.
The two coding harnesses differ in exactly ONE expression — both declare
`requires = [SandboxCapability]` and accept the same local-process sandbox
shape, so the messages, the abort bridge and the whole sandbox middleware stay
shared. Codex's config moved verbatim into `codexAdapter()`; only indentation
changed (26 of its 27 body lines are byte-identical).
`engine` DEFAULTS TO `"codex"`, so Arm C — which passes nothing — is unaffected.
Arm A opts in.
WHY ARM A SWITCHED: codex's adapter reads the CLI's own item schema and
SYNTHESISES the `web_search` arguments it never receives, so every observed call
reached the console as `{"query":""}`. The claude-code adapter reads assistant
`tool_use` blocks, which carry the model's arguments verbatim. Measured: the
query lands in both `TOOL_CALL_ARGS.args` and `TOOL_CALL_END.input`. It also
needs none of codex's three workarounds — no TOML quote-in-quote for reasoning,
no `skipGitRepoCheck`, no API key (it runs on an existing `claude` login).
THE MODEL PIN IS LOAD-BEARING. Claude models from 4.7 onward return no reasoning
TEXT through Claude Code: thinking blocks and `thinking_delta`s arrive with an
empty `thinking` field, because the API's `display` defaults to `"omitted"` and
the CLI exposes no flag to request summaries. Measured on the `sonnet` alias: 14
`REASONING_*` chunks carrying zero characters; the same probe on
`claude-opus-4-6` streamed real reasoning. A newer id yields a console that
prints commands and thinks in silence.
`as-tool.test.ts` gains the one guard no other gate provides: drop the `engine`
argument and lint, typecheck, build and every other test stay green while the
empty-query defect silently returns. Verified by deleting the argument — that
test failed and nothing else did.
Also updates the comments the swap falsified rather than deleting them, and the
console's idle-state copy, which named the codex binary.
CAVEAT: pnpm-lock.yaml carries ~999 lines of peer-dependency re-resolution noise
(jiti, @babel/core, vue-component-type-helpers across eslint/babel/vue tooling)
picked up incidentally by the install. Only 2 new resolutions are genuinely
this change's; no `@ag-ui/*` lines moved.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tp3i7qBNzWC9xVzsaz5KTZ
CopilotKit Examples
This directory contains 51 consolidated demo repositories showcasing CopilotKit integrations, canvas apps, and showcases.
Each example is a self-contained project. To get started:
GIT_LFS_SKIP_SMUDGE=1 git clone <repo-url>
cd examples/<category>/<name>
# Follow the example's own README for setup instructions
Note: The
v1/andv2/directories at the top level are legacy workspace examples from earlier CopilotKit releases and are not part of the consolidated demo set.
Integrations (19)
Framework integration starters demonstrating CopilotKit with various agent frameworks.
| Example | Description |
|---|---|
| langgraph-python | Starter template for building AI agents using LangGraph (Python) and CopilotKit |
| langgraph-js | Starter template for building AI agents using LangGraph (JS) with Turborepo monorepo |
| langgraph-fastapi | Starter template for building AI agents using LangGraph with FastAPI and Poetry |
| mastra | Starter template for building AI agents using Mastra and CopilotKit |
| crewai-flows | Starter template for building AI agents using CrewAI Flows (uv-based) |
| llamaindex | Starter template with a LlamaIndex investment analyst agent |
| pydantic-ai | Starter template with a PydanticAI investment analyst agent |
| ms-agent-framework-python | CopilotKit with Microsoft Agent Framework (Python/FastAPI, AG-UI protocol) |
| ms-agent-framework-dotnet | CopilotKit with Microsoft Agent Framework (.NET/C#, AG-UI protocol) |
| strands-python | Starter template with a Strands investment analyst agent |
| mcp-apps | Integration of MCP Apps with CopilotKit using Three.js |
| adk | Starter template using Google ADK with an investment analyst agent |
| agent-spec | Starter for Agent Spec with A2UI-powered frontend tool rendering |
| a2a-a2ui | Starter for A2UI + A2A with a restaurant finder agent (Gemini/ADK) |
| agno | Starter template using Agno with an investment analyst agent |
| crewai-crews | Starter template for building AI agents using CrewAI Crews |
| a2a-middleware | Multi-agent starter with A2A Protocol and AG-UI Protocol (LangGraph + ADK) |
| claude-sdk-python | Starter template using the Claude Agent SDK (Python) and CopilotKit |
| claude-sdk-typescript | Starter template using the Claude Agent SDK (TypeScript) and CopilotKit |
Canvas (7)
AI-powered canvas applications with visual card interfaces, real-time state sync, and HITL workflows.
| Example | Description |
|---|---|
| langgraph-python | AG-UI canvas starter with LangGraph — interactive cards with real-time AI sync |
| llamaindex | AG-UI canvas starter with LlamaIndex — visual cards, multi-step planning, HITL |
| llamaindex-composio | Hackathon starter with LlamaIndex, CopilotKit, and Composio (Google Sheets integration) |
| pydantic-ai | AG-UI canvas starter with PydanticAI — visual cards, planning, HITL |
| mastra | AG-UI canvas starter with Mastra — interactive cards with real-time AI sync |
| gemini | Open Gemini Canvas — post generator and stack analyzer agents (Gemini + LangGraph) |
| mastra-pm | AG-UI + Mastra workshop — shared state, multiple clients, generative UI |
Showcases (25)
Full-featured demo applications highlighting CopilotKit capabilities in real-world scenarios.
| Example | Description |
|---|---|
| banking | Banking app demo with authorization, multiple operations, and generative UI |
| presentation | PowerPoint-like web app built with CopilotKit |
| deep-agents | Deep research assistant with planning, memory/files, and generative UI (Tavily) |
| deep-agents-job-search | Job application assistant — resume parsing, skill extraction, DeepAgents orchestration |
| generative-ui | Generative UI for agentic apps — AG-UI protocol showcase |
| generative-ui-playground | Playground for static GenUI, MCP Apps, and A2UI generative UI types |
| grok-generative-ui | grok-4.6 searches X server-side, then composes the dashboard from real components |
| mcp-apps | MCP Apps demo — airline booking, hotel booking, investment simulator, kanban board |
| research-canvas | ANA (Agent Native Application) — research canvas with Tavily search and LangGraph |
| mcp-demo | Working Memory — MCP server-client integration for project management (Linear) |
| strands-file-analyzer | AI-powered document analysis with Strands Agents and Amazon Bedrock |
| microsoft-kanban | Kanban board demo with CopilotKit + Microsoft Agent Framework (.NET, AG-UI) |
| multi-page | Multi-page Remix app with CopilotKit |
| orca | Cisco CopilotKit demo — PR and repository analytics dashboard |
| pydantic-ai-todos | AI-powered todo board with PydanticAI (Todo, In-Progress, Done columns) |
| scene-creator | Scene creator with LangGraph + Gemini 3 — AI-generated characters and backgrounds |
| adk-dashboard | Generative canvas with Google ADK — metrics, charts, and real-time data |
| langgraph-js-support-agents | Multi-agent telecom support system with intent, lookup, reply, and escalation agents |
| multi-agent-canvas | Open Multi-Agent Canvas — manage multiple agents (travel, research, MCP) in one chat |
| chatkit-studio | Open ChatKit Studio — explore and build embeddable chat experiences |
| enterprise-brex | Enterprise banking demo with authorization, operations, and generative UI |
| a2a-travel | A2A + AG-UI multi-agent travel demo (LangGraph + Google ADK) |
| spreadsheet | AI-powered Excel-like spreadsheet web app |
| todo | Simple todo app built with CopilotKit |
| strands-crm | Enterprise sales CRM — dashboard, pipeline, products, quotes, reports & agentic canvas (TypeScript Strands + AG-UI) |