# copilotkit - Doramagic AI Context Pack

> Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated.

## Sufficiency Principle

- **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary.
- **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work.

## How the Host AI Should Use This

You are reading the AI Context Pack that Doramagic compiled for copilotkit. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project.

## Claim Consumption Rules

- **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure.
- **Minimum status for a fact**: `supported`
- `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path.
- `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying.
- `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact.
- `unverified`: Must not be used as fact; state clearly that evidence is insufficient.
- `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf.

## Who It Fits Best

- **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0004` supported 0.86
- **Users who want to bring professional workflows into a host AI**: The repo contains Skill documents. Evidence: `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-builder/SKILL.md`, `packages/a2ui-renderer/skills/a2ui-renderer/SKILL.md` et al. Claim: `clm_0005` supported 0.86

## What It Can Do

- **AI Skill / Agent Instruction Asset Library** (Previewable before install): The project contains Skill or Agent instruction files that a host AI can read, useful for bringing professional workflows into hosts like Claude, Codex, or Cursor. Evidence: `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-builder/SKILL.md`, `packages/a2ui-renderer/skills/a2ui-renderer/SKILL.md` et al. Claim: `clm_0001` supported 0.86
- **Multi-Host Install and Distribution** (Verify after install): The project contains plugin or marketplace configuration, indicating it targets install and distribution across one or more AI hosts. Evidence: `.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json` Claim: `clm_0002` unverified 0.25
- **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `README.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/references/foundations/quickstart.md`, `packages/angular/README.md`, `packages/channels-discord/README.md` et al. Claim: `clm_0003` supported 0.86

## How to Start

- `npx copilotkit@latest create` Evidence: `README.md` Claim: `clm_0006` supported 0.86
- `npx copilotkit@latest skills install` Evidence: `README.md` Claim: `clm_0007` supported 0.86
- `npx create-ag-ui-app my-agent-app` Evidence: `README.md` Claim: `clm_0008` supported 0.86
- `npm install @copilotkit/angular` Evidence: `packages/angular/README.md` Claim: `clm_0009` unverified 0.25
- `pnpm add @copilotkit/channels` Evidence: `packages/channels/README.md` Claim: `clm_0010` unverified 0.25, `clm_0011` unverified 0.25, `clm_0012` unverified 0.25, `clm_0013` unverified 0.25 et al.
- `pnpm add @copilotkit/channels-core @copilotkit/channels-slack` Evidence: `packages/channels/README.md` Claim: `clm_0011` unverified 0.25
- `pnpm add @copilotkit/channels-discord @copilotkit/channels @copilotkit/channels-ui` Evidence: `packages/channels-discord/README.md` Claim: `clm_0012` unverified 0.25
- `pnpm add @copilotkit/channels-slack @copilotkit/channels @copilotkit/channels-ui` Evidence: `packages/channels-slack/README.md` Claim: `clm_0013` unverified 0.25
- `pnpm add @copilotkit/channels @copilotkit/channels-ui @copilotkit/channels-teams` Evidence: `packages/channels-teams/README.md` Claim: `clm_0014` unverified 0.25
- `npx @microsoft/m365agentsplayground   # opens http://localhost:56150` Evidence: `packages/channels-teams/README.md` Claim: `clm_0015` unverified 0.25

## Continue-or-Stop Decision Card

- **Current recommendation**: Sandbox-trial permissions first
- **Why**: The project has signals of install commands, host configuration, or local writes; do not go straight into your primary environment—trial it in isolation first.

### 30-Second Read

- **What to do now**: Sandbox-trial permissions first
- **Minimum safe next step**: Run Prompt Preview first; if you still want to install, trial only in an isolated environment
- **Do not trust yet**: Tool permission boundaries cannot be trusted before install.
- **Continuing will touch**: Command execution, Host AI configuration, Local environment or project files

### What You Can Trust Now

- **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0004` supported 0.86
- **Target-audience signal: Users who want to bring professional workflows into a host AI** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-builder/SKILL.md`, `packages/a2ui-renderer/skills/a2ui-renderer/SKILL.md` et al. Claim: `clm_0005` supported 0.86
- **Capability exists: AI Skill / Agent Instruction Asset Library** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-builder/SKILL.md`, `packages/a2ui-renderer/skills/a2ui-renderer/SKILL.md` et al. Claim: `clm_0001` supported 0.86
- **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `README.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/references/foundations/quickstart.md`, `packages/angular/README.md`, `packages/channels-discord/README.md` et al. Claim: `clm_0003` supported 0.86
- **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `README.md` Claim: `clm_0006` supported 0.86

### What You Cannot Trust Yet

- **Tool permission boundaries cannot be trusted before install.** (unverified): MCP/tool projects usually touch files, the network, the browser, or external APIs, so permissions and logs must be checked for real.
- **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project.
- **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment.
- **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. Evidence: `.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `AGENTS.md`, `CLAUDE.md` et al.
- **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first.
- **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment. Evidence: `.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json`
- **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.
- **Do the install commands require network access, permissions, or global writes?** (unverified): This affects install risk in both enterprise and personal environments. Evidence: `README.md`

### What Continuing Will Touch

- **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `README.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/references/foundations/quickstart.md`, `packages/angular/README.md`, `packages/channels-discord/README.md` et al.
- **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `AGENTS.md`, `CLAUDE.md` et al.
- **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json`, `README.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/references/foundations/quickstart.md` et al.
- **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts.

### Minimum Safe Next Steps

- **Run Prompt Preview first**: Use a pre-install interactive trial to judge whether the way of working fits; it needs no authorization or environment change. (applies when: Applies to any project, especially when output quality is unknown.)
- **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.)
- **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.)
- **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.)

### Exit Plan

- **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable.
- **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state.
- **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually.
- **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck.

## What Can Only Be Previewed

- Explain who the project fits and what it can do
- Demonstrate a typical conversation flow based on project docs
- Help the user decide whether it is worth installing or researching further

## What Must Be Verified After Install

- Actually installing the Skill, plugin, or CLI
- Running scripts, modifying local files, or accessing external services
- Verifying real output quality, performance, and compatibility

## Boundary & Risk Decision Card

- **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0028` inferred 0.45
- **Host AI plugin or Skill rule conflicts**: New rules may change how the user's existing host AI behaves. Mitigation: Inspect the plugin manifest and Skill files before installing, and test in isolation if needed. Evidence: `.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json` Claim: `clm_0029` inferred 0.45
- **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/references/foundations/quickstart.md`, `packages/angular/README.md`, `packages/channels-discord/README.md` et al. Claim: `clm_0030` supported 0.86
- **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment.
- **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.
- **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments.

## Pre-Work Working Context

### Loading Order

- First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset.
- Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative.
- Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match.
- When you need to carry out a concrete task, check role_skill_index first, then evidence_index.
- For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required.

### Task Routes

- **AI Skill / Agent Instruction Asset Library**: Use role_skill_index / evidence_index to help the user pick a usable role, Skill, or workflow first. Boundary: Can be experienced via a pre-install Prompt. Evidence: `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/SKILL.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-builder/SKILL.md`, `packages/a2ui-renderer/skills/a2ui-renderer/SKILL.md` et al. Claim: `clm_0001` supported 0.86
- **Multi-Host Install and Distribution**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `.claude-plugin/marketplace.json`, `.claude-plugin/plugin.json`
- **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `README.md`, `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/references/foundations/quickstart.md`, `packages/angular/README.md`, `packages/channels-discord/README.md` et al. Claim: `clm_0003` supported 0.86

### Context Scale

- Total files: 16006
- Important-file coverage: 40/16006
- Evidence index entries: 96
- Role / Skill entries: 17

### Handling Insufficient Evidence

- **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts.
- **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install.
- **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run.
- **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version.

## Prompt Recipes

### Fit assessment

- Goal: Judge whether this project fits the user's current task.
- Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation.

```text
Based on the AI Context Pack for copilotkit, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id.
```

### Pre-install experience

- Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise.
- Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language.

```text
Treat copilotkit as a pre-install experience asset, not an already-installed tool or a real runtime environment.

Output exactly four parts:
1. Ask me 3 necessary questions first.
2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow.
3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run.
4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project.

Hard boundaries:
- Do not claim you have installed, run, executed tests, modified files, or produced real results.
- Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing".
- If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...".
- The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating".
- Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment.
- Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions.

```

### Role / Skill selection

- Goal: Pick the best-matching asset from the project's roles or Skills.
- Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed.

```text
Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs.
```

### Risk pre-check

- Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting.
- Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items.

```text
Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have.
```

### Host AI kickoff instruction

- Goal: Turn the project context into a host AI instruction for the start of a conversation.
- Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI.

```text
Based on the AI Context Pack for copilotkit, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results.
```

## Role / Skill Index

- Indexed 17 role / Skill / project-doc entries.

- **chatgpt-app-builder** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “chatgpt-app-builder”, use it for a pre-install experience first, then decide whether to install. Evidence: `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/SKILL.md`
- **mcp-apps-builder** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “mcp-apps-builder”, use it for a pre-install experience first, then decide whether to install. Evidence: `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-apps-builder/SKILL.md`
- **mcp-builder** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “mcp-builder”, use it for a pre-install experience first, then decide whether to install. Evidence: `examples/showcases/open-mcp-client/apps/mcp-use-server/.agent/skills/mcp-builder/SKILL.md`
- **a2ui-renderer** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “a2ui-renderer”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/a2ui-renderer/skills/a2ui-renderer/SKILL.md`
- **react-core** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “react-core”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/react-core/skills/react-core/SKILL.md`
- **runtime** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “runtime”, use it for a pre-install experience first, then decide whether to install. Evidence: `packages/runtime/skills/runtime/SKILL.md`
- **a2ui-renderer** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “a2ui-renderer”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/a2ui-renderer/SKILL.md`
- **copilotkit-agui** (skill): Use when building custom agent backends, implementing the AG-UI protocol, debugging streaming issues, or understanding how agents communicate with frontends. Covers event types, SSE transport, AbstractAgent/HttpAgent patterns, state synchronization, tool calls, and human-in-the-loop flows. Activation hint: When the user's task is highly relevant to the workflow described by “copilotkit-agui”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/copilotkit-agui/SKILL.md`
- **copilotkit-contribute** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “copilotkit-contribute”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/copilotkit-contribute/SKILL.md`
- **copilotkit-debug** (skill): Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing. Activation hint: When the user's task is highly relevant to the workflow described by “copilotkit-debug”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/copilotkit-debug/SKILL.md`
- **copilotkit-develop** (skill): Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime. Activation hint: When the user's task is highly relevant to the workflow described by “copilotkit-develop”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/copilotkit-develop/SKILL.md`
- **copilotkit-integrations** (skill): Use when wiring an external agent framework LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others into a CopilotKit application via the AG-UI protocol. Activation hint: When the user's task is highly relevant to the workflow described by “copilotkit-integrations”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/copilotkit-integrations/SKILL.md`
- **copilotkit-self-update** (skill): Use when the user wants to update, refresh, or reinstall the CopilotKit agent SKILLS the SKILL.md files that teach this agent about CopilotKit . NOT for updating the CopilotKit codebase or project — this is specifically about refreshing the skills/knowledge this agent has loaded. Triggers on "update copilotkit skills", "update skills", "refresh skills", "skills are stale", "skills are outdated", "get latest skills",… Activation hint: When the user's task is highly relevant to the workflow described by “copilotkit-self-update”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/copilotkit-self-update/SKILL.md`
- **copilotkit-setup** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “copilotkit-setup”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/copilotkit-setup/SKILL.md`
- **copilotkit-upgrade** (skill): Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes. Activation hint: When the user's task is highly relevant to the workflow described by “copilotkit-upgrade”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/copilotkit-upgrade/SKILL.md`
- **react-core** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “react-core”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/react-core/SKILL.md`
- **runtime** (skill):  Activation hint: When the user's task is highly relevant to the workflow described by “runtime”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/runtime/SKILL.md`

## Evidence Index

- Indexed 96 evidence entries.

- **teach-mode cookbook** (documentation): A reusable recipe for building self-learning, teachable CopilotKit demos. Evidence: `examples/showcases/banking/docs/teach-mode/README.md`
- **General Guidelines for working with Nx** (documentation): General Guidelines for working with Nx Evidence: `AGENTS.md`
- **General Guidelines for working with Nx** (documentation): General Guidelines for working with Nx Evidence: `CLAUDE.md`
- **CopilotKit** (documentation): Docs https://docs.copilotkit.ai/?ref=github readme · Examples https://www.copilotkit.ai/examples · Enterprise Intelligence Platform https://go.copilotkit.ai/enterprise-intelligence-platform · Discord https://discord.gg/6dffbvGU3D?ref=github readme Evidence: `README.md`
- **CopilotKit Examples** (documentation): This directory contains 50 consolidated demo repositories showcasing CopilotKit integrations, canvas apps, and showcases. Evidence: `examples/README.md`
- **CopilotKit Python SDK** (documentation): ! PyPI version https://badge.fury.io/py/copilotkit.svg https://badge.fury.io/py/copilotkit ! License: MIT https://img.shields.io/badge/License-MIT-yellow.svg https://opensource.org/licenses/MIT Evidence: `sdk-python/README.md`
- **Showcase — Agent Guidance canonical** (documentation): Showcase — Agent Guidance canonical Evidence: `showcase/AGENTS.md`
- **Showcase** (documentation): See AGENTS.md ./AGENTS.md in this directory — it is the canonical guidance for all showcase work the non-negotiable iron rules for showcase cells, the single-source symlink mechanism, and the preflight/value-test checklist . Read it before touching any integration, test, fixture, or frontend under showcase/ . Evidence: `showcase/CLAUDE.md`
- **Showcase Platform** (documentation): Tagline: agent entry point for the showcase docs tree and from-scratch local setup. The fanout block below routes you to the right procedural doc. Evidence: `showcase/README.md`
- **Hacktoberfest 2025: Contribute to CopilotKit and Win Exclusive Swag!** (documentation): ! hacktoberfest banner https://github.com/user-attachments/assets/813f2f32-999e-4e91-a527-9c1748380154 Evidence: `community/content/README.md`
- **Open Gemini Canvas** (documentation): https://github.com/user-attachments/assets/1e95c9e1-2d55-4f63-b805-be49fe94a493 Evidence: `examples/canvas/gemini/README.md`
- **CopilotKit < LangGraph AG-UI Canvas Starter** (documentation): CopilotKit < LangGraph AG-UI Canvas Starter Evidence: `examples/canvas/langgraph-python/README.md`
- **Fullstack Agents Hackathon Starter** (documentation): Welcome to the Fullstack Agents hackathon! This starter gives you a complete AI-powered canvas application with real-world integrations. Utilizing LlamaIndex https://developers.llamaindex.ai , Composio https://docs.composio.dev , and CopilotKit https://docs.copilotkit.ai . Evidence: `examples/canvas/llamaindex-composio/README.md`
- **Llama Index Agent Starter: Python** (documentation): This package is a quick starter example for building AG-UI agents with Llama Index and CopilotKit. Evidence: `examples/canvas/llamaindex-composio/agent/README.md`
- **CopilotKit < LlamaIndex AG-UI Canvas Starter** (documentation): CopilotKit < LlamaIndex AG-UI Canvas Starter Evidence: `examples/canvas/llamaindex/README.md`
- **Llama Index Agent Starter: Python** (documentation): This package is a quick starter example for building AG-UI agents with Llama Index and CopilotKit. Evidence: `examples/canvas/llamaindex/agent/README.md`
- **AG-UI Mastra Workshop** (documentation): A comprehensive workshop demonstrating AG-UI Agent User Interaction protocol with Mastra integration. This workshop shows how to build sophisticated AI applications with shared state, multiple client interfaces, and rich user interactions. Evidence: `examples/canvas/mastra-pm/README.md`
- **CopilotKit < Mastra AG-UI Canvas Starter** (documentation): CopilotKit < Mastra AG-UI Canvas Starter Evidence: `examples/canvas/mastra/README.md`
- **CopilotKit < PydanticAI AG-UI Canvas Starter** (documentation): CopilotKit < PydanticAI AG-UI Canvas Starter Evidence: `examples/canvas/pydantic-ai/README.md`
- **parity/ — integration-demo parity tooling** (documentation): parity/ — integration-demo parity tooling Evidence: `examples/integrations/_parity/README.md`
- **CopilotKit < A2A + A2UI Starter** (documentation): This is a starter template for building AI agents that use A2UI https://a2ui.org and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated restaurant finder agent that can find restaurants and book reservations Evidence: `examples/integrations/a2a-a2ui/README.md`
- **A2UI Extension Implementation** (documentation): This is the Python implementation of the a2ui extension. Evidence: `examples/integrations/a2a-a2ui/a2ui_extension/README.md`
- **A2UI Restaurant finder and table reservation agent sample.** (documentation): A2UI Restaurant finder and table reservation agent sample. Evidence: `examples/integrations/a2a-a2ui/agent/README.md`
- **A2A + AG-UI Multi-Agent Starter** (documentation): A minimal starter template for building multi-agent applications with A2A Protocol Agent-to-Agent and AG-UI Protocol Agent-UI . This project demonstrates how to coordinate multiple AI agents across different frameworks LangGraph and Google ADK to solve tasks collaboratively. Evidence: `examples/integrations/a2a-middleware/README.md`
- **CopilotKit < ADK Starter** (documentation): This is a starter template for building AI agents using Google's ADK https://google.github.io/adk-docs/ and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated investment analyst agent that can research stocks, analyze market data, and provide investment insights. Evidence: `examples/integrations/adk/README.md`
- **CopilotKit < Agent Spec Starter** (documentation): This is a starter template for building AI agents using Agent Spec and CopilotKit. It provides a modern Next.js application wired to a FastAPI backend that serves an Agent Spec agent with A2UI-powered frontend tool rendering calendar, inbox, email compose, daily brief dashboard . Evidence: `examples/integrations/agent-spec/README.md`
- **CopilotKit + AWS AgentCore** (documentation): Chat UI with generative charts, shared-state todo canvas, and inline tool rendering — deployed on AWS Bedrock AgentCore. Pick LangGraph or Strands. Evidence: `examples/integrations/agentcore/README.md`
- **Terraform Infrastructure** (documentation): Equivalent of ../infra-cdk/ using Terraform. Evidence: `examples/integrations/agentcore/infra-terraform/README.md`
- **CopilotKit < Agno Starter** (documentation): This is a starter template for building AI agents using Agno https://agno.com and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated investment analyst agent that can research stocks, analyze market data, and provide investment insights. Evidence: `examples/integrations/agno/README.md`
- **CopilotKit × Claude Agent SDK — Python Starter** (documentation): CopilotKit × Claude Agent SDK — Python Starter Evidence: `examples/integrations/claude-sdk-python/README.md`
- **CopilotKit × Claude Agent SDK — TypeScript Starter** (documentation): CopilotKit × Claude Agent SDK — TypeScript Starter Evidence: `examples/integrations/claude-sdk-typescript/README.md`
- **CopilotKit < CrewAI Crew Starter** (documentation): This is a starter template for building AI agents using CrewAI Crews https://docs.crewai.com/en/concepts/crews and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated CrewAI Crew agent to be built on top of. Evidence: `examples/integrations/crewai-crews/README.md`
- **CopilotKit < CrewAI Flow Starter** (documentation): This is a starter template for building AI agents using CrewAI Flows https://docs.crewai.com/en/concepts/flows and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated CrewAI Flow agent to be built on top of. Evidence: `examples/integrations/crewai-flows/README.md`
- **CopilotKit < LangGraph Starter** (documentation): This is a starter template for building AI agents using LangGraph https://www.langchain.com/langgraph and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated LangGraph agent to be built on top of. Evidence: `examples/integrations/langgraph-fastapi/README.md`
- **CopilotKit < LangGraph Starter** (documentation): This is a starter template for building AI agents using LangGraph https://www.langchain.com/langgraph and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated LangGraph agent TypeScript to be built on top of. Evidence: `examples/integrations/langgraph-js/README.md`
- **CopilotKit + LangGraph Todo Demo** (documentation): This repository serves as both a showcase and template for building AI agents with CopilotKit and LangGraph. It demonstrates how CopilotKit can drive interactive UI beyond just chat, using a collaborative todo list as the primary example. Evidence: `examples/integrations/langgraph-python/CLAUDE.md`
- **CopilotKit < LangGraph Starter** (documentation): This is a starter template for building AI agents using LangGraph https://www.langchain.com/langgraph and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated LangGraph agent to be built on top of. Evidence: `examples/integrations/langgraph-python/README.md`
- **CopilotKit < LlamaIndex Starter** (documentation): This is a starter template for building AI agents using LlamaIndex https://llamaindex.com and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated investment analyst agent that can research stocks, analyze market data, and provide investment insights. Evidence: `examples/integrations/llamaindex/README.md`
- **Llama Index Agent Starter: Python** (documentation): This package is a quick starter example for building AG-UI agents with Llama Index and CopilotKit. Evidence: `examples/integrations/llamaindex/agent/README.md`
- **CopilotKit < Mastra Starter** (documentation): This is a starter template for building AI agents using Mastra https://mastra.ai and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with integrated AI capabilities and a beautiful UI. Evidence: `examples/integrations/mastra/README.md`
- **CopilotKit < MCP Apps Starter** (documentation): This is a starter template for integrating MCP Apps https://mcpui.dev with CopilotKit https://copilotkit.ai . It uses the Three.js example https://github.com/modelcontextprotocol/ext-apps/tree/main/examples/threejs-server from the official Model Context Protocol organization on GitHub. Evidence: `examples/integrations/mcp-apps/README.md`
- **Example: Three.js App** (documentation): Interactive 3D scene renderer using Three.js. Demonstrates streaming code preview and full MCP App integration. Evidence: `examples/integrations/mcp-apps/threejs-server/README.md`
- **CopilotKit < Microsoft Agent Framework Starter** (documentation): CopilotKit < Microsoft Agent Framework Starter Evidence: `examples/integrations/ms-agent-framework-dotnet/README.md`
- **CopilotKit < Microsoft Agent Framework Python** (documentation): CopilotKit < Microsoft Agent Framework Python Evidence: `examples/integrations/ms-agent-framework-python/README.md`
- **CopilotKit < PydanticAI Starter** (documentation): This is a starter template for building AI agents using PydanticAI https://ai.pydantic.dev/ and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated investment analyst agent that can research stocks, analyze market data, and provide investment insights. Evidence: `examples/integrations/pydantic-ai/README.md`
- **CopilotKit < strands Starter** (documentation): This is a starter template for building AI agents using strands https://strands.com and CopilotKit https://copilotkit.ai . It provides a modern Next.js application with an integrated investment analyst agent that can research stocks, analyze market data, and provide investment insights. Evidence: `examples/integrations/strands-python/README.md`
- **CopilotKit x ShadCN** (documentation): https://github.com/user-attachments/assets/f0059b04-ad68-4563-ad7a-e574c64e42d0 Evidence: `examples/shadcn/README.md`
- **AG-UI + A2A Multi-Agent Communication Demo** (documentation): AG-UI + A2A Multi-Agent Communication Demo Evidence: `examples/showcases/a2a-travel/README.md`
- **A2UI PDF Analyst** (documentation): Chat with your PDF and watch the agent build the UI for each answer. Powered by A2UI v0.9 Agent-to-UI — the open protocol that lets an agent describe a surface as structured component operations your frontend renders against its own design system. Same chat input, two rendering strategies, one shared 21-component catalog. Evidence: `examples/showcases/a2ui-pdf-analyst/README.md`
- **Repository Guidelines** (documentation): Project Structure & Module Organization Evidence: `examples/showcases/adk-dashboard/AGENTS.md`
- **CopilotKit + ADK Generative Canvas** (documentation): https://github.com/user-attachments/assets/9201d528-573f-43cc-9d31-571c362318a7 Evidence: `examples/showcases/adk-dashboard/README.md`
- **Arcade × CopilotKit Cookbook** (documentation): Give CopilotKit's Built-in Agent authenticated tools Gmail, Google News through Arcade https://www.arcade.dev , and render the OAuth step as generative UI in the chat. Evidence: `examples/showcases/arcade-tools/README.md`
- **Northwind Finance — CopilotKit v2 Banking Demo** (documentation): Northwind Finance — CopilotKit v2 Banking Demo Evidence: `examples/showcases/banking/README.md`
- **Open ChatKit Studio** (documentation): Explore and build embeddable chat experiences. Evidence: `examples/showcases/chatkit-studio/README.md`
- **CopilotKit Chat Playground** (documentation): A visual playground for customizing CopilotKit chat components. Adjust colors, fonts, and text, then export production-ready code. Evidence: `examples/showcases/chatkit-studio/apps/playground/README.md`
- **🌍 CopilotKit World Explorer** (documentation): Interactive world travel app demonstrating CopilotKit and AG-UI protocol integration with LangGraph agents. Evidence: `examples/showcases/chatkit-studio/apps/world/README.md`
- **CopilotKit × Daytona — runCode showcase** (documentation): CopilotKit × Daytona — runCode showcase Evidence: `examples/showcases/daytona-runcode/README.md`
- **Job Application Assistant** (documentation): A Job assistant built with CopilotKit http://copilotkit.ai/ Next.js on the frontend and DeepAgents https://github.com/langchain-ai/deepagents by LangChain on the backend. Users upload their resume PDF , the system extracts skills and context and DeepAgents orchestrate sub-agents & tools to search the web via Tavily for relevant job postings. Results stream back to the UI in real time and are rendered alongside the chat. Evidence: `examples/showcases/deep-agents-job-search/README.md`
- **Deep Research Assistant** (documentation): A CopilotKit https://copilotkit.ai Deep Agents demo showcasing planning, memory/files, and generative UI using Tavily https://www.tavily.com/ for web research. Evidence: `examples/showcases/deep-agents/README.md`
- **CopilotKit Demo App** (documentation): This demo application highlights the capabilities of CopilotKit by demonstrating how to build an app that emphasizes authorization, supports multiple operations, and incorporates generative UI elements. The banking application scenario serves as a practical example of these features in action. Evidence: `examples/showcases/enterprise-brex/README.md`
- The remaining 36 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`.

## Rules the Host AI Must Follow

- **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `examples/showcases/banking/docs/teach-mode/README.md`, `AGENTS.md`, `CLAUDE.md`
- **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `examples/showcases/banking/docs/teach-mode/README.md`, `AGENTS.md`, `CLAUDE.md`

## Questions the User Should Answer First

- Which host AI or local environment do you plan to use it in?
- Do you just want to experience the workflow first, or are you ready to actually install?
- What matters most to you: install cost, output quality, or conflicts with your existing rules?

## Acceptance Checks

- Every capability claim can be traced back to a file path in evidence_refs.
- AI_CONTEXT_PACK.md does not package previews as a real run.
- The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes.

---

## Doramagic Context Augmentation

The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints.

## Human Manual Outline

Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph.

Host AI hard rules:
- Do not treat page titles, section order, summaries, or importance values as factual project evidence.
- When explaining the Human Manual outline, state that it is only a reading route or salience signal.
- Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph.

- **Repository Overview & Monorepo Architecture**: importance `high`
  - source_paths: README.md, package.json, nx.json, migrations.json, AGENTS.md
- **Multi-Platform Frontend Adapters (React, Angular, Vue, React Native, Slack, Teams)**: importance `high`
  - source_paths: packages/angular/src/lib/copilotkit.ts, packages/angular/src/lib/components/chat/copilot-chat-view.ts, packages/angular/src/lib/agent.ts, examples/v2/vue/demo/app.vue, examples/v2/vue/demo/pages/index.vue
- **AG-UI Protocol, A2UI & MCP Apps Generative UI**: importance `high`
  - source_paths: packages/a2ui-renderer/src/index.ts, packages/a2ui-renderer/src/a2ui-types.ts, packages/a2ui-renderer/src/react-renderer/core/A2UIRenderer.tsx, packages/a2ui-renderer/src/react-renderer/core/A2UIProvider.tsx, packages/a2ui-renderer/src/react-renderer/create-catalog.tsx
- **Agent Framework Integrations & CopilotKit Intelligence**: importance `high`
  - source_paths: examples/integrations/langgraph-python/agent/agent.py, examples/integrations/langgraph-js/agent/src/agent.ts, examples/integrations/langgraph-fastapi/agent/main.py, examples/integrations/adk/agent/main.py, examples/integrations/crewai-crews/agent/src/latest_ai_development/crew.py

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `56c67a346fe4e924fb41877afa95c1a7bf943a94`
- inspected_files: `README.md`, `package.json`, `pnpm-lock.yaml`, `docs/README.md`, `docs/model-allowlist.json`, `docs/next.config.ts`, `docs/package-lock.json`, `docs/package.json`, `docs/public/fonts/plus-jakarta-sans/SOURCE.md`, `docs/src/app/[framework]/[[...slug]]/__tests__/framework-root-shell-layout.test.ts`, `docs/src/app/__tests__/globals-css.test.ts`, `docs/src/app/__tests__/public-assets.test.ts`, `docs/src/app/frontends/[frontend]/[...slug]/page.test.ts`, `docs/src/app/llms-full.txt/route.ts`, `docs/src/app/llms-mdx/[[...slug]]/route.test.ts`, `docs/src/app/llms-mdx/[[...slug]]/route.ts`, `docs/src/app/llms.txt/route.ts`, `docs/src/app/robots.ts`, `docs/src/app/sitemap.ts`, `docs/src/components/content/index.ts`

Host AI hard rules:
- Without repo_clone_verified=true, do not claim that the source code has been read.
- Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts.
- Without quick_start_verified=true, do not claim that the Quick Start path has run successfully.

## Doramagic Pitfall Constraints

These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes.

### Constraint 1: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.57.4
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.57.4. Context: Observed when using node, python
- Why it matters: Upgrade or migration may change expected behavior: v1.57.4
- Evidence: failure_mode_cluster:github_release | https://github.com/CopilotKit/CopilotKit/releases/tag/v1.57.4
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 2: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.58.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.58.0. Context: Observed when using node
- Why it matters: Upgrade or migration may change expected behavior: v1.58.0
- Evidence: failure_mode_cluster:github_release | https://github.com/CopilotKit/CopilotKit/releases/tag/v1.58.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 3: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.59.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.59.0. Context: Observed when using node, python
- Why it matters: Upgrade or migration may change expected behavior: v1.59.0
- Evidence: failure_mode_cluster:github_release | https://github.com/CopilotKit/CopilotKit/releases/tag/v1.59.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 4: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.59.1
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.59.1. Context: Observed when using node, python, playwright
- Why it matters: Upgrade or migration may change expected behavior: v1.59.1
- Evidence: failure_mode_cluster:github_release | https://github.com/CopilotKit/CopilotKit/releases/tag/v1.59.1
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 5: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.59.2
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.59.2. Context: Observed when using node
- Why it matters: Upgrade or migration may change expected behavior: v1.59.2
- Evidence: failure_mode_cluster:github_release | https://github.com/CopilotKit/CopilotKit/releases/tag/v1.59.2
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 6: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.59.3
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.59.3. Context: Observed when using node
- Why it matters: Upgrade or migration may change expected behavior: v1.59.3
- Evidence: failure_mode_cluster:github_release | https://github.com/CopilotKit/CopilotKit/releases/tag/v1.59.3
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.