livekit-agents

Name: livekit-agents
Author: livekit

61stars11forks

How to install livekit-agents?

livekit/agent-skills/livekit-agents

$npx -y skills add livekit/agent-skills --skill livekit-agents

Installs into the current project.

Summary

Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Provides opinionated guidance for the

Files · 1

View on GitHub

SKILL.md

1	# LiveKit Agents Development for LiveKit Cloud
2
3	This skill provides opinionated guidance for building voice AI agents with LiveKit Cloud. It assumes you are using LiveKit Cloud (the recommended path) and encodes how to approach agent development, not API specifics. All factual information about APIs, methods, and configurations must come from live documentation.
4
5	This skill is for LiveKit Cloud developers. If you're self-hosting LiveKit, some recommendations (particularly around LiveKit Inference) won't apply directly.
6
7	## MANDATORY: Read This Checklist Before Starting
8
9	Before writing ANY code, complete this checklist:
10
11	1. Read this entire skill document - Do not skip sections even if MCP is available
12	2. Ensure LiveKit Cloud project is connected - You need `LIVEKIT_URL`, `LIVEKIT_API_KEY`, and `LIVEKIT_API_SECRET` from your Cloud project
13	3. Set up documentation access - Use MCP if available, otherwise use web search
14	4. Plan to write tests - Every agent implementation MUST include tests (see testing section below)
15	5. Verify all APIs against live docs - Never rely on model memory for LiveKit APIs
16
17	This checklist applies regardless of whether MCP is available. MCP provides documentation access but does NOT replace the guidance in this skill.
18
19	## LiveKit Cloud Setup
20
21	LiveKit Cloud is the fastest way to get a voice agent running. It provides:
22	- Managed infrastructure (no servers to deploy)
23	- LiveKit Inference for AI models (no separate API keys needed)
24	- Built-in noise cancellation, turn detection, and other voice features
25	- Simple credential management
26
27	### Connect to Your Cloud Project
28
29	1. Sign up at [cloud.livekit.io](https://cloud.livekit.io) if you haven't already
30	2. Create a project (or use an existing one)
31	3. Get your credentials from the project settings:
32	- `LIVEKIT_URL` - Your project's WebSocket URL (e.g., `wss://your-project.livekit.cloud`)
33	- `LIVEKIT_API_KEY` - API key for authentication
34	- `LIVEKIT_API_SECRET` - API secret for authentication
35
36	4. Set these as environment variables (typically in `.env.local`):
37	```bash
38	LIVEKIT_URL=wss://your-project.livekit.cloud
39	LIVEKIT_API_KEY=your-api-key
40	LIVEKIT_API_SECRET=your-api-secret
41	```
42
43	The LiveKit CLI can automate credential setup. Consult the CLI documentation for current commands.
44
45	### Use LiveKit Inference for AI Models
46
47	LiveKit Inference is the recommended way to use AI models with LiveKit Cloud. It provides access to leading AI model providers—all through your LiveKit credentials with no separate API keys needed.
48
49	Benefits of LiveKit Inference:
50	- No separate API keys to manage for each AI provider
51	- Billing consolidated through your LiveKit Cloud account
52	- Optimized for voice AI workloads
53
54	Consult the documentation for available models, supported providers, and current usage patterns. The documentation always has the most up-to-date information.
55
56	## Critical Rule: Never Trust Model Memory for LiveKit APIs
57
58	LiveKit Agents is a fast-evolving SDK. Model training data is outdated the moment it's created. When working with LiveKit:
59
60	- Never assume API signatures, method names, or configuration options from memory
61	- Never guess SDK behavior or default values
62	- Always verify against live documentation before writing code
63	- Always cite the documentation source when implementing features
64
65	This rule applies even when confident about an API. Verify anyway.
66
67	## REQUIRED: Use LiveKit MCP Server for Documentation
68
69	Before writing any LiveKit code, ensure access to the LiveKit documentation MCP server. This provides current, verified API information and prevents reliance on stale model knowledge.
70
71	### Check for MCP Availability
72
73	Look for `livekit-docs` MCP tools. If available, use them for all documentation lookups:
74	- Search documentation before implementing any feature
75	- Verify API signatures and method parameters
76	- Look up configuration options and their valid values
77	- Find working examples for the specific task at hand
78
79	### If MCP Is Not Available
80
81	If the LiveKit MCP server is not configured, inform the user and recommend installation. Installation instructions for all supported platforms are available at:
82
83	https://docs.livekit.io/intro/mcp-server/
84
85	Fetch the installation instructions appropriate for the user's coding agent from that page.
86
87	### Fallback When MCP Unavailable
88
89	If MCP cannot be installed in the current session:
90	1. Inform the user immediately that documentation cannot be verified in real-time
91	2. Use web search

People who liked this also viewed

6 picks

Type

livekit-agents

61stars11forks

View on GitHub

How to install livekit-agents?

livekit/agent-skills/livekit-agents

$npx -y skills add livekit/agent-skills --skill livekit-agents

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LiveKit Agents Development for LiveKit Cloud
2
3	This skill provides opinionated guidance for building voice AI agents with LiveKit Cloud. It assumes you are using LiveKit Cloud (the recommended path) and encodes how to approach agent development, not API specifics. All factual information about APIs, methods, and configurations must come from live documentation.
4
5	This skill is for LiveKit Cloud developers. If you're self-hosting LiveKit, some recommendations (particularly around LiveKit Inference) won't apply directly.
6
7	## MANDATORY: Read This Checklist Before Starting
8
9	Before writing ANY code, complete this checklist:
10
11	1. Read this entire skill document - Do not skip sections even if MCP is available
12	2. Ensure LiveKit Cloud project is connected - You need `LIVEKIT_URL`, `LIVEKIT_API_KEY`, and `LIVEKIT_API_SECRET` from your Cloud project
13	3. Set up documentation access - Use MCP if available, otherwise use web search
14	4. Plan to write tests - Every agent implementation MUST include tests (see testing section below)
15	5. Verify all APIs against live docs - Never rely on model memory for LiveKit APIs
16
17	This checklist applies regardless of whether MCP is available. MCP provides documentation access but does NOT replace the guidance in this skill.
18
19	## LiveKit Cloud Setup
20
21	LiveKit Cloud is the fastest way to get a voice agent running. It provides:
22	- Managed infrastructure (no servers to deploy)
23	- LiveKit Inference for AI models (no separate API keys needed)
24	- Built-in noise cancellation, turn detection, and other voice features
25	- Simple credential management
26
27	### Connect to Your Cloud Project
28
29	1. Sign up at [cloud.livekit.io](https://cloud.livekit.io) if you haven't already
30	2. Create a project (or use an existing one)
31	3. Get your credentials from the project settings:
32	- `LIVEKIT_URL` - Your project's WebSocket URL (e.g., `wss://your-project.livekit.cloud`)
33	- `LIVEKIT_API_KEY` - API key for authentication
34	- `LIVEKIT_API_SECRET` - API secret for authentication
35
36	4. Set these as environment variables (typically in `.env.local`):
37	```bash
38	LIVEKIT_URL=wss://your-project.livekit.cloud
39	LIVEKIT_API_KEY=your-api-key
40	LIVEKIT_API_SECRET=your-api-secret
41	```
42
43	The LiveKit CLI can automate credential setup. Consult the CLI documentation for current commands.
44
45	### Use LiveKit Inference for AI Models
46
47	LiveKit Inference is the recommended way to use AI models with LiveKit Cloud. It provides access to leading AI model providers—all through your LiveKit credentials with no separate API keys needed.
48
49	Benefits of LiveKit Inference:
50	- No separate API keys to manage for each AI provider
51	- Billing consolidated through your LiveKit Cloud account
52	- Optimized for voice AI workloads
53
54	Consult the documentation for available models, supported providers, and current usage patterns. The documentation always has the most up-to-date information.
55
56	## Critical Rule: Never Trust Model Memory for LiveKit APIs
57
58	LiveKit Agents is a fast-evolving SDK. Model training data is outdated the moment it's created. When working with LiveKit:
59
60	- Never assume API signatures, method names, or configuration options from memory
61	- Never guess SDK behavior or default values
62	- Always verify against live documentation before writing code
63	- Always cite the documentation source when implementing features
64
65	This rule applies even when confident about an API. Verify anyway.
66
67	## REQUIRED: Use LiveKit MCP Server for Documentation
68
69	Before writing any LiveKit code, ensure access to the LiveKit documentation MCP server. This provides current, verified API information and prevents reliance on stale model knowledge.
70
71	### Check for MCP Availability
72
73	Look for `livekit-docs` MCP tools. If available, use them for all documentation lookups:
74	- Search documentation before implementing any feature
75	- Verify API signatures and method parameters
76	- Look up configuration options and their valid values
77	- Find working examples for the specific task at hand
78
79	### If MCP Is Not Available
80
81	If the LiveKit MCP server is not configured, inform the user and recommend installation. Installation instructions for all supported platforms are available at:
82
83	https://docs.livekit.io/intro/mcp-server/
84
85	Fetch the installation instructions appropriate for the user's coding agent from that page.
86
87	### Fallback When MCP Unavailable
88
89	If MCP cannot be installed in the current session:
90	1. Inform the user immediately that documentation cannot be verified in real-time
91	2. Use web search

People who liked this also viewed

6 picks

Type