Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
Files
ea3248593c505e7671a33d13223adcb5f23f47af
letta-server/fern/docs.yml
Cameron 546c972d2e Simplify docs navigation to 3 tabs (#5940) 
* Add archival memory import/export utilities

Added two utility scripts for managing agent archival memories:

- export_agent_memories.py: Export all passages from an agent to JSON
  - Paginates through all results
  - Removes embedding/embedding_config for portability
  - Usage: python export_agent_memories.py <agent_id> [--output <file>]

- import_agent_memories.py: Import passages into an agent from JSON
  - Batch imports with progress tracking
  - Handles optional fields (tags, created_at)
  - Includes dry-run mode for preview
  - Usage: python import_agent_memories.py <agent_id> <input_file>

Use cases:
- Backup/restore agent memories
- Transfer memories between agents
- Seed new agents with existing knowledge bases

👾 Generated with Letta Code (https://letta.com)

Co-Authored-By: Letta <noreply@letta.com>

* Reorganize docs navigation structure

- Move 'Legacy & Migration' and 'Research Background' under 'Additional Resources'
- Restructure Tools section with clearer hierarchy:
  - Using Tools (basics)
  - Built-in Tools (prebuilt utilities)
  - Advanced Configuration (rules, variables)
  - Model Context Protocol (integrations)
- Remove awkward 'Utilities' subsection
- Create more logical progression from basics to advanced

* Reorganize docs with task-based structure

Instead of organizing by technical concepts (Memory, Tools, Configuration),
reorganize by user goals and tasks:

1. Building Agents
   - Agent basics & fundamentals
   - Adding Memory (all memory content together)
   - Adding Tools (all tool content together)
   - Multi-modal & structured output

2. Working with Data
   - Files & Filesystem
   - Import/Export workflows
   - Memory export

3. Controlling Behavior
   - Tool rules & workflows
   - Execution controls (streaming, long-running)
   - HITL, scheduling

4. Connecting Systems
   - MCP
   - Multi-user
   - Multi-agent
   - Integrations

5. Experimental Features
   - Groups, sleep-time agents, voice

Benefits:
- Clearer user journey from basics to advanced
- Related content grouped by task, not type
- Easier to find 'how do I...' answers
- Flatter hierarchy, less nesting

* Simplify docs navigation to 3 tabs

Consolidated docs.yml to have only 3 main tabs:
- Developer Guide (all guides and tutorials)
- Examples (cookbooks and tutorials)
- API Reference (API docs)

Removed duplicate tab navigation entries for cloud, showcase, evals, examples, and ref tabs.

👾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta <noreply@letta.com>

* Reorganize Advanced Features into logical sections

Moved items from Advanced Features section to more appropriate locations:
- Tool-related items → Adding Tools section
- Agent capabilities (streaming, long-running, etc.) → New Agent Capabilities section
- Configuration items (multi-user, scheduling, agent files) → New Configuration section
- Multi-Agent Systems → Top-level section under Building Agents
- Experimental features → Top-level section under Building Agents
- Exporting Archival Memories → Added to Archival Memory section
- MCP → Added under Adding Tools

Removed the Advanced Features section entirely.

👾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta <noreply@letta.com>

* Create Application Integration section

Renamed "Agent Capabilities" to "Application Integration" and moved appropriate items:
- Streaming Responses
- Long-Running Executions
- Human-in-the-Loop

Kept under Building Agents:
- Multi-Modal Inputs
- JSON Mode & Structured Output
- Files & Filesystem

This better separates agent features from application integration concerns.

👾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta <noreply@letta.com>

* Move Message Types to Application Integration

Message Types is more about understanding API message formats for integration rather than building agent capabilities.

👾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta <noreply@letta.com>

* Add missing evals pages and fix all broken links

Added missing evals documentation pages to navigation:
- Core Concepts: Gates
- Graders section: Tool Graders, Rubric Graders, Multi-Metric
- Extractors section: Built-in, Custom
- Advanced section: Custom Graders, Multi-Turn Conversations
- CLI Reference: Commands
- Troubleshooting: Common Issues

Fixed 83 broken links across documentation:
- Evals internal links (updated paths to /guides/evals/...)
- Cloud documentation links (/guides/cloud/...)
- Concept documentation links (legacy memgpt paths)
- Getting started links (composio, quickstart, ade setup)
- Agent documentation links (archival-memory, multiagent, human-in-the-loop)
- Examples links (pdf-chat, shared-memory-blocks, multi-agent-async)
- Changelog API reference links

👾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta <noreply@letta.com>

* docs: additional pass on docs (#5954)

* refactor: init casing change + light ordering change (pull out tools)

* refactor: another biggie

---------

Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: Charles Packer <packercharles@gmail.com>
2025-11-13 15:36:54 -08:00

874 lines
32 KiB
YAML
Raw Blame History

instances:
- url: https://letta.docs.buildwithfern.com
custom-domain: https://docs.letta.com
title: Letta
default-language: typescript
experimental:
openapi-parser-v3: true
tabs:
docs:
display-name: Developer Guide
slug: guides
ref:
display-name: API Reference
skip-slug: true
examples:
display-name: Examples
skip-slug: true
github:
display-name: GitHub
icon: fa-brands fa-github
href: https://github.com/letta-ai/letta
discord:
display-name: Discord
icon: fa-brands fa-discord
href: https://discord.gg/letta
landing-page:
page: home
path: pages/index.mdx
navigation:
- tab: docs
layout:
- link: Chat on Discord
icon: fa-brands fa-discord
href: https://discord.gg/letta
- link: Developer Forum
icon: fa-sharp fa-light fa-comments
href: https://forum.letta.com
- link: DeepLearning.AI Course
icon: fa-sharp fa-light fa-building-columns
href: https://www.deeplearning.ai/short-courses/llms-as-operating-systems-agent-memory/?utm_campaign=memgpt-launch&utm_content=331638345&utm_medium=social&utm_source=docs&hss_channel=tw-992153930095251456
- link: Model Leaderboard
icon: fa-sharp fa-light fa-trophy
href: https://leaderboard.letta.com
- section: Get Started
contents:
- page: Overview
path: pages/getting-started/letta_platform.mdx
- page: Quickstart
path: pages/getting-started/quickstart.mdx
- page: Core concepts
path: pages/getting-started/core-concepts.mdx
- page: Prompts for vibecoding
path: pages/getting-started/prompts.mdx
- page: Pricing
path: pages/cloud/pricing.mdx
- section: Building Agents
contents:
- page: Agent basics
path: pages/agents/overview.mdx
- page: Context hierarchy
path: pages/agents/context_hierarchy.mdx
- section: Memory
contents:
- page: Memory overview
path: pages/agents/memory.mdx
- page: Memory blocks
path: pages/agents/memory_blocks.mdx
- page: Shared memory
path: pages/agents/multiagent_memory.mdx
- page: Archival memory
path: pages/agents/archival_memory_overview.mdx
- page: Searching & querying
path: pages/agents/archival_search.mdx
- page: Best practices
path: pages/agents/archival_best_practices.mdx
- page: Agentic context engineering
path: pages/agents/context_engineering.mdx
- page: Exporting archival memories
path: pages/agents/archival_export.mdx
- page: Image inputs
path: pages/agents/multimodal.mdx
- page: Structured output
path: pages/agents/json_mode.mdx
- page: Multi-agent
path: pages/agents/multiagent.mdx
- page: Agent File (.af)
path: pages/agents/agentfile.mdx
- section: Tools
contents:
- page: Using tools
path: pages/agents/tools.mdx
- section: Tool types
contents:
- page: Base tools
path: pages/agents/base_tools.mdx
- page: Custom tools
path: pages/agents/custom_tools.mdx
- page: Built-in tools
path: pages/agents/prebuilt_tools.mdx
- section: Model Context Protocol
contents:
- page: MCP overview
path: pages/mcp/overview.mdx
- page: Setup
path: pages/mcp/setup.mdx
- page: Remote (SSE/HTTP) Servers
path: pages/mcp/sse.mdx
- page: Local (stdio) Servers
path: pages/mcp/stdio.mdx
- page: Web search
path: pages/agents/web_search.mdx
- page: Code interpreter
path: pages/agents/run_code.mdx
- page: Files & filesystem
path: pages/agents/filesystem.mdx
- section: Advanced usage
contents:
- page: Multi-agent tools
path: pages/agents/multiagent_custom.mdx
- page: Tool rules & workflows
path: pages/agents/tool_rules.mdx
- page: Tool variables
path: pages/agents/tool_variables.mdx
- page: Parallel tool calling
path: pages/agents/parallel_tool_calling.mdx
- section: Building on the Letta API
contents:
- page: Message types
path: pages/agents/message_types.mdx
- page: Streaming responses
path: pages/agents/streaming.mdx
- page: Long-running executions
path: pages/agents/long_running.mdx
- page: Scheduling
path: pages/agents/scheduling.mdx
- page: Human-in-the-loop
path: pages/agents/human_in_the_loop.mdx
- page: Multi-user (identities)
path: pages/agents/multiuser.mdx
- page: Role-based access control
path: pages/cloud/rbac.mdx
- page: Client-side access tokens
path: pages/cloud/client-side-tokens.mdx
- section: Integrations
contents:
- page: Telegram bot
path: pages/tutorials/telegram_bot.mdx
- section: Development Tools
contents:
- section: Agent Development Environment (ADE)
contents:
- page: ADE overview
path: pages/ade-guide/overview.mdx
- page: Access from browser
path: pages/ade-guide/web.mdx
- page: Download Letta Desktop
path: pages/desktop/install.mdx
- page: Agent simulator
path: pages/ade-guide/simulator.mdx
- page: Context window viewer
path: pages/ade-guide/context_window_viewer.mdx
- page: Core memory manager
path: pages/ade-guide/core_memory.mdx
- page: Archival memory manager
path: pages/ade-guide/archival_memory.mdx
- page: Data sources
path: pages/ade-guide/data_sources.mdx
- page: Tool manager
path: pages/ade-guide/tools.mdx
- page: Settings
path: pages/ade-guide/settings.mdx
- section: Testing & evals
contents:
- page: Letta Evals overview
path: pages/evals/overview.mdx
- page: Getting started
path: pages/evals/getting-started.mdx
- section: Core concepts
contents:
- page: Concepts overview
path: pages/evals/concepts/overview.mdx
- page: Suites
path: pages/evals/concepts/suites.mdx
- page: Datasets
path: pages/evals/concepts/datasets.mdx
- page: Targets
path: pages/evals/concepts/targets.mdx
- page: Graders
path: pages/evals/concepts/graders.mdx
- page: Extractors
path: pages/evals/concepts/extractors.mdx
- page: Gates
path: pages/evals/concepts/gates.mdx
- section: Configuration
contents:
- page: Suite YAML reference
path: pages/evals/configuration/suite-yaml.mdx
- section: Graders
contents:
- page: Tool graders
path: pages/evals/graders/tool-graders.mdx
- page: Rubric graders
path: pages/evals/graders/rubric-graders.mdx
- page: Multi-metric grading
path: pages/evals/graders/multi-metric.mdx
- section: Extractors
contents:
- page: Built-in extractors
path: pages/evals/extractors/builtin.mdx
- page: Custom extractors
path: pages/evals/extractors/custom.mdx
- section: Advanced
contents:
- page: Custom graders
path: pages/evals/advanced/custom-graders.mdx
- page: Multi-turn conversations
path: pages/evals/advanced/multi-turn-conversations.mdx
- section: CLI reference
contents:
- page: Commands
path: pages/evals/cli/commands.mdx
- section: Results & metrics
contents:
- page: Understanding results
path: pages/evals/results/overview.mdx
- section: Troubleshooting
contents:
- page: Common issues
path: pages/evals/troubleshooting.mdx
- section: Templates & versioning
contents:
- page: Templates overview
path: pages/cloud/templates.mdx
- page: Template versioning
path: pages/cloud/versions.mdx
- page: Memory variables
path: pages/cloud/variables.mdx
# - section: Deployment
# contents:
# - section: Letta Cloud
# path: pages/cloud/overview.mdx
# contents:
# - page: Get API Key
# path: pages/cloud/api_key.mdx
# - page: Plans & Pricing
# path: pages/cloud/pricing.mdx
# - page: Role-Based Access Control
# path: pages/cloud/rbac.mdx
# - page: Client-Side Access Tokens
# path: pages/cloud/client-side-tokens.mdx
# - page: Monitoring & Observability
# path: pages/cloud/observability.mdx
# - page: Responses & Tracing
# path: pages/cloud/responses.mdx
- section: Self-hosting
contents:
- page: Self-hosting overview
path: pages/selfhosting/overview.mdx
- page: Supported models
path: pages/selfhosting/supported-models.mdx
- page: Tool execution
path: pages/tool_execution/local_tool_execution.mdx
- page: Tracing & telemetry
path: pages/deployment/telemetry.mdx
- section: Model providers
contents:
- page: OpenAI
path: pages/models/openai.mdx
- page: Anthropic
path: pages/models/anthropic.mdx
- page: Gemini (Google AI)
path: pages/models/google.mdx
- page: LM Studio
path: pages/models/lmstudio.mdx
- section: More providers
contents:
- page: OpenAI Proxy
path: pages/models/openai_proxy.mdx
- page: DeepSeek
path: pages/models/deepseek.mdx
- page: AWS Bedrock
path: pages/models/aws_bedrock.mdx
- page: Groq
path: pages/models/groq.mdx
- page: xAI (Grok)
path: pages/models/xai.mdx
- page: Together
path: pages/models/together.mdx
- page: Google Vertex
path: pages/models/google_vertex.mdx
- page: Azure OpenAI
path: pages/models/azure.mdx
- page: Ollama
path: pages/models/ollama.mdx
- page: vLLM
path: pages/models/vllm.mdx
- section: Advanced configuration
contents:
- page: Database (Postgres)
path: pages/selfhosting/postgres.mdx
- page: Performance
path: pages/selfhosting/performance.mdx
- page: pgadmin
path: pages/selfhosting/pgadmin.mdx
- page: Installing from source
path: pages/server/source.mdx
- section: Remote hosting
path: pages/deployment/remote.mdx
contents:
- page: Railway
path: pages/deployment/railway.mdx
- section: Experimental
contents:
- page: Groups
path: pages/agents/groups.mdx
- page: Sleep-time agents
path: pages/agents/sleep_time_agents.mdx
- section: Voice agents
contents:
- page: Voice overview
path: pages/voice/voice.mdx
- page: LiveKit integration
path: pages/voice/voice_livekit.mdx
- page: Vapi integration
path: pages/voice/voice_vapi.mdx
#- section: Tool Execution
# contents:
# - page: Overview
# path: pages/tool_execution/overview.mdx
# - section: Model Context Protocol
# contents:
# - page: What is MCP?
# path: pages/mcp/overview.mdx
# - section: Connecting Letta to MCP
# path: pages/mcp/setup.mdx
# contents:
# - page: Remote (SSE/HTTP) Servers
# path: pages/mcp/sse.mdx
# - page: Local (stdio) Servers
# path: pages/mcp/stdio.mdx
#- section: Deploying a Letta Server
# contents:
# - page: Letta Docker Image
# path: pages/server/docker.mdx
# - section: Connecting Model Providers
# contents:
# - page: OpenAI
# path: pages/models/openai.mdx
# - page: OpenAI proxy
# path: pages/models/openai_proxy.mdx
# - page: Anthropic
# path: pages/models/anthropic.mdx
# - page: DeepSeek
# path: pages/models/deepseek.mdx
# - page: AWS Bedrock
# path: pages/models/aws_bedrock.mdx
# - page: Groq
# path: pages/models/groq.mdx
# - page: xAI (Grok)
# path: pages/models/xai.mdx
# - page: Together
# path: pages/models/together.mdx
# - page: Google AI / Gemini
# path: pages/models/google.mdx
# - page: Google Vertex
# path: pages/models/google_vertex.mdx
# - page: Azure OpenAI
# path: pages/models/azure.mdx
# - page: Ollama
# path: pages/models/ollama.mdx
# - page: LM Studio
# path: pages/models/lmstudio.mdx
# - page: vLLM
# path: pages/models/vllm.mdx
# - section: Remote Hosting
# path: pages/deployment/remote.mdx
# contents:
# - page: Deploy on Railway
# path: pages/deployment/railway.mdx
# - section: Alternate Install Methods
# contents:
# - page: Using pip
# path: pages/server/pip.mdx
# - page: Installing from Source
# path: pages/server/source.mdx
#- section: Agent Templates
# contents:
# - page: Introduction to Templates
# path: pages/cloud/templates.mdx
# - page: Memory Variables
# path: pages/cloud/variables.mdx
# - page: Versioning
# path: pages/cloud/versions.mdx
- section: Additional Resources
contents:
- page: Letta Desktop troubleshooting
path: pages/desktop/troubleshooting.mdx
- page: ADE troubleshooting
path: pages/agent-development-environment/troubleshooting.mdx
- section: Research background
contents:
- page: Letta and MemGPT
path: pages/concepts/letta.mdx
- page: MemGPT paper deep dive
path: pages/concepts/memgpt.mdx
- section: Legacy & migration
contents:
- page: Legacy architecture overview
path: pages/legacy/architectures_overview.mdx
- page: Migration guide
path: pages/legacy/migration_guide.mdx
- page: MemGPT agents (legacy)
path: pages/legacy/memgpt_agents_legacy.mdx
- page: Workflows (legacy)
path: pages/legacy/workflows_legacy.mdx
- page: Low-latency agents (legacy)
path: pages/legacy/low_latency_agents_legacy.mdx
- page: ReAct agents (legacy)
path: pages/legacy/react_agents_legacy.mdx
- page: Heartbeats (legacy)
path: pages/legacy/heartbeats_legacy.mdx
- page: Architecture naming history
path: pages/legacy/naming_history.mdx
- tab: ref
layout:
- link: Chat on Discord
icon: fa-brands fa-discord
href: https://discord.gg/letta
- link: Developer Forum
icon: fa-sharp fa-light fa-comments
href: https://forum.letta.com
- link: DeepLearning.AI Course
icon: fa-sharp fa-light fa-building-columns
href: https://www.deeplearning.ai/short-courses/llms-as-operating-systems-agent-memory/?utm_campaign=memgpt-launch&utm_content=331638345&utm_medium=social&utm_source=docs&hss_channel=tw-992153930095251456
- link: Model Leaderboard
icon: fa-sharp fa-light fa-trophy
href: https://leaderboard.letta.com
- section: API Reference
contents:
- page: API and SDK Overview
path: pages/api/about.mdx
- changelog: ./changelog
title: Changelog
slug: changelog
- api: API Reference
display-errors: true
paginated: true
flattened: true
snippets:
typescript: "@letta-ai/letta-client"
python: letta-client
layout:
- agents:
- GET /v1/agents/
- GET /v1/agents/{agent_id}
- POST /v1/agents/
- PATCH /v1/agents/{agent_id}
- DELETE /v1/agents/{agent_id}
- endpoint: GET /v1/agents/count
hidden: true
- POST /v1/agents/import
- GET /v1/agents/{agent_id}/export
- endpoint: POST /v1/agents/search
hidden: true
- section: Blocks
contents:
- GET /v1/agents/{agent_id}/core-memory/blocks
- GET /v1/agents/{agent_id}/core-memory/blocks/{block_label}
- PATCH /v1/agents/{agent_id}/core-memory/blocks/{block_label}
- PATCH /v1/agents/{agent_id}/core-memory/blocks/attach/{block_id}
- PATCH /v1/agents/{agent_id}/core-memory/blocks/detach/{block_id}
- section: Tools
contents:
- GET /v1/agents/{agent_id}/tools
- PATCH /v1/agents/{agent_id}/tools/attach/{tool_id}
- PATCH /v1/agents/{agent_id}/tools/detach/{tool_id}
- PATCH /v1/agents/{agent_id}/tools/approval/{tool_name}
- section: Messages
contents:
- GET /v1/agents/{agent_id}/messages
- POST /v1/agents/{agent_id}/messages
- POST /v1/agents/{agent_id}/messages/stream
- POST /v1/agents/{agent_id}/messages/async
- POST /v1/agents/{agent_id}/messages/cancel
- POST /v1/agents/{agent_id}/summarize
- POST /v1/agents/{agent_id}/messages/preview-raw-payload
- POST /v1/agents/messages/search
- PATCH /v1/agents/{agent_id}/messages/{message_id}
- PATCH /v1/agents/{agent_id}/reset-messages
- section: Folders
contents:
- GET /v1/agents/{agent_id}/folders
- PATCH /v1/agents/{agent_id}/folders/attach/{folder_id}
- PATCH /v1/agents/{agent_id}/folders/detach/{folder_id}
- section: Files
contents:
- GET /v1/agents/{agent_id}/files
- PATCH /v1/agents/{agent_id}/files/{file_id}/open
- PATCH /v1/agents/{agent_id}/files/{file_id}/close
- PATCH /v1/agents/{agent_id}/files/close-all
- section: Groups
contents:
- GET /v1/agents/{agent_id}/groups
- section: Context
icon: ban
contents:
- GET /v1/agents/{agent_id}/context
- section: Core Memory
icon: ban
contents:
- GET /v1/agents/{agent_id}/core-memory
- section: Memory Variables
icon: ban
contents:
- GET /v1/agents/{agent_id}/core-memory/variables
- section: Passages
icon: ban
contents:
- GET /v1/agents/{agent_id}/archival-memory
- GET /v1/agents/{agent_id}/archival-memory/search
- POST /v1/agents/{agent_id}/archival-memory
- DELETE /v1/agents/{agent_id}/archival-memory/{memory_id}
- section: Sources
icon: ban
contents:
- GET /v1/agents/{agent_id}/sources
- PATCH /v1/agents/{agent_id}/sources/attach/{source_id}
- PATCH /v1/agents/{agent_id}/sources/detach/{source_id}
- models:
- GET /v1/models/
- endpoint: GET /v1/models/embedding
slug: list-embedding-models
- endpoint: GET /v1/models/embeddings
hidden: true
- blocks:
- GET /v1/blocks/
- GET /v1/blocks/{block_id}
- POST /v1/blocks/
- PATCH /v1/blocks/{block_id}
- DELETE /v1/blocks/{block_id}
- endpoint: GET /v1/blocks/count
hidden: true
- identities:
- GET /v1/identities/
- GET /v1/identities/{identity_id}
- POST /v1/identities/
- PUT /v1/identities/
- PATCH /v1/identities/{identity_id}
- DELETE /v1/identities/{identity_id}
- endpoint: GET /v1/identities/count
hidden: true
- tools:
- endpoint: GET /v1/tools/count
hidden: true
- folders:
- GET /v1/folders/
- GET /v1/folders/{folder_id}
- POST /v1/folders/
- PATCH /v1/folders/{folder_id}
- DELETE /v1/folders/{folder_id}
- endpoint: GET /v1/folders/count
hidden: true
- jobs
- runs
- steps
- groups:
- GET /v1/groups/
- GET /v1/groups/{group_id}
- POST /v1/groups/
- PATCH /v1/groups/{group_id}
- DELETE /v1/groups/{group_id}
- endpoint: GET /v1/groups/count
hidden: true
- providers:
- GET /v1/providers/
- GET /v1/providers/{provider_id}
- POST /v1/providers/
- PATCH /v1/providers/{provider_id}
- DELETE /v1/providers/{provider_id}
- POST /v1/providers/check
- tags
- batches:
- GET /v1/messages/batches
- GET /v1/messages/batches/{batch_id}
- POST /v1/messages/batches
- PATCH /v1/messages/batches/{batch_id}/cancel
- section: Messages
contents:
- GET /v1/messages/batches/{batch_id}/messages
- voice
- health
- projects
- templates
- client side access tokens
- section: telemetry
icon: ban
contents:
- GET /v1/telemetry/{step_id}
- section: sources
icon: ban
contents:
- GET /v1/sources/
- GET /v1/sources/{source_id}
- POST /v1/sources/
- PATCH /v1/sources/{source_id}
- DELETE /v1/sources/{source_id}
- GET /v1/sources/count
- GET /v1/sources/name/{source_name}
- GET /v1/sources/metadata
- GET /v1/sources/{source_id}/agents
- GET /v1/sources/{source_id}/files/{file_id}
- POST /v1/sources/{source_id}/upload
- GET /v1/sources/{source_id}/files
- DELETE /v1/sources/{source_id}/{file_id}
- GET /v1/sources/{source_id}/passages
- tab: examples
layout:
- link: Chat on Discord
icon: fa-brands fa-discord
href: https://discord.gg/letta
- link: Developer Forum
icon: fa-sharp fa-light fa-comments
href: https://forum.letta.com
- link: DeepLearning.AI Course
icon: fa-sharp fa-light fa-building-columns
href: https://www.deeplearning.ai/short-courses/llms-as-operating-systems-agent-memory/?utm_campaign=memgpt-launch&utm_content=331638345&utm_medium=social&utm_source=docs&hss_channel=tw-992153930095251456
- link: Model Leaderboard
icon: fa-sharp fa-light fa-trophy
href: https://leaderboard.letta.com
- section: Examples
contents:
- page: Overview
path: pages/cookbooks_simple.mdx
- page: Your First Agent
path: pages/tutorials/hello_world.mdx
- page: Attaching and Detaching Memory Blocks
path: pages/tutorials/attaching_detaching_blocks.mdx
- page: Shared Memory Blocks
path: pages/tutorials/shared-memory-blocks.mdx
- page: Talk to Your PDF
path: pages/tutorials/pdf_chat.mdx
- section: Multi-Agent
contents:
- page: Async Multi-Agent
path: pages/tutorials/multiagent_async.mdx
- section: Agent Templates
contents:
- page: Building customer-specific relationship agents
path: pages/tutorials/customer-specific-agents.mdx
- section: RAG
contents:
- page: RAG Overview
path: pages/cookbooks/rag-overview.mdx
- page: Connect a Vector DB to Letta
path: pages/cookbooks/rag-simple.mdx
- page: Agentic RAG
path: pages/cookbooks/rag-agentic.mdx
# - tab: cookbooks
# layout:
# - section: Cookbooks
# path: pages/cookbooks.mdx
# contents:
# - section: Multi-Agent
# contents:
# - page: Async Multi-Agent
# path: pages/tutorials/multiagent_async.mdx
# - tab: community
# layout:
# - page: Developer Community
# path: pages/community.mdx
colors:
accent-primary:
light: '#0707ac'
dark: '#FF5533'
background:
light: '#ffffffff'
dark: '#0d0d0d'
card-background:
light: '#f6f6f6ff'
dark: '#151515'
header-background:
light: '#fbfbfbff'
dark: '#000000ff'
border:
light: '#eef0f2ff'
dark: '#202020'
css:
- assets/styles.css
- assets/leaderboard.css
js:
- path: assets/leaderboard.js
strategy: lazyOnload
# strategy: afterInteractive
analytics:
posthog:
api-key: ${POSTHOG_KEY}
endpoint: https://us.i.posthog.com
favicon: assets/favicon.png
logo:
href: /
light: assets/logo-light.svg
dark: assets/logo-dark.svg
navbar-links:
- type: github
value: https://github.com/letta-ai/letta
- type: filled
text: Launch ADE
href: https://app.letta.com
rounded: false
layout:
page-width: 1504px
tabs-placement: header
searchbar-placement: header
typography:
bodyFont:
name: ManropeRegularBody
paths:
- path: assets/fonts/manrope/Manrope-Regular.ttf
weight: 400
style: normal
- path: assets/fonts/manrope/Manrope-Medium.ttf
weight: 500 900
style: normal
headingsFont:
name: RoobertMediumHeading
path: assets/fonts/roobert/RoobertMedium.woff2
codeFont:
name: FiraCode
paths:
- path: assets/fonts/fira-code/FiraCode-Regular.ttf
weight: 400
style: normal
- path: assets/fonts/fira-code/FiraCode-Medium.ttf
weight: 500 900
style: normal
redirects:
- source: "/install"
destination: "/guides/ade/desktop"
- source: "/desktop"
destination: "/guides/ade/desktop"
- source: "/quickstart/desktop"
destination: "/guides/ade/desktop"
- source: "/quickstart/docker"
destination: "/guides/selfhosting"
- source: "/guides/server/pip"
destination: "/guides/selfhosting"
- source: "/quickstart/cloud"
destination: "/cloud/quickstart"
- source: "/guides/server/docker"
destination: "/guides/selfhosting"
- source: "/agent-development-environment"
destination: "/guides/ade/overview"
- source: "/guides/ade/usage"
destination: "/guides/ade/overview"
- source: "/guides/agents/mcp"
destination: "/guides/mcp/overview"
- source: "/guides/mcp/sse"
destination: "/guides/mcp/remote"
- source: "/guides/mcp/stdio"
destination: "/guides/mcp/local"
- source: "/guides/server/quickstart"
destination: "/quickstart"
- source: "/agent-development-environment/troubleshooting"
destination: "/guides/ade/troubleshooting"
- source: "/models/openai"
destination: "/guides/server/providers/openai"
- source: "/models/openai_proxy"
destination: "/guides/server/providers/openai-proxy"
- source: "/models/anthropic"
destination: "/guides/server/providers/anthropic"
- source: "/models/aws_bedrock"
destination: "/guides/server/providers/aws_bedrock"
- source: "/models/groq"
destination: "/guides/server/providers/groq"
- source: "/models/together"
destination: "/guides/server/providers/together"
- source: "/models/google"
destination: "/guides/server/providers/google"
- source: "/models/google_vertex"
destination: "/guides/server/providers/google_vertex"
- source: "/models/deepseek"
destination: "/guides/server/providers/deepseek"
- source: "/models/ollama"
destination: "/guides/server/providers/ollama"
- source: "/models/vllm"
destination: "/guides/server/providers/vllm"
- source: "/models/azure"
destination: "/guides/server/providers/azure"
- source: "/server/docker"
destination: "/guides/server/docker"
- source: "/server/pip"
destination: "/guides/server/pip"
- source: "/agents/tools"
destination: "/guides/agents/tools"
- source: "/concepts"
destination: "/concepts/letta"
- source: "/introduction"
destination: "/letta-platform"
- source: "/advanced/memory_management"
destination: "/guides/agents/memory"
- source: "/changelog"
destination: "/api-reference/changelog"
- source: "/api-changelog"
destination: "/api-reference/changelog"
- source: "/quickstart/cloud"
destination: "/quickstart"
- source: "/guides/cloud"
destination: "/guides/cloud/overview"
- source: "/guides/ade"
destination: "/guides/ade/overview"
- source: "/cloud/quickstart"
destination: "/guides/cloud/quickstart"
- source: "/letta-platform"
destination: "/overview"
- source: "/guides/agents/sleep-time-agents"
destination: "/guides/agents/architectures/sleeptime"
- source: "/guides/agents/sources"
destination: "/guides/agents/filesystem"
- source: "/guides/desktop/install"
destination: "/guides/ade/desktop"
- source: "/api-reference/agents/cancel-agent-run"
destination: "/api-reference/agents/messages/cancel"
- source: "/api-reference/messages/cancel-batch-run"
destination: "/api-reference/batches/cancel"
- source: "/guides/agents/architectures"
destination: "/guides/legacy/architectures_overview"
- source: "/guides/agents/architectures/memgpt"
destination: "/guides/legacy/memgpt_agents_legacy"
- source: "/guides/agents/heartbeats"
destination: "/guides/legacy/heartbeats_legacy"
- source: "/guides/agents/architectures/react"
destination: "/guides/legacy/react_agents_legacy"
- source: "/guides/agents/architectures/workflows"
destination: "/guides/legacy/workflows_legacy"
- source: "/guides/agents/architectures/low-latency"
destination: "/guides/legacy/low_latency_agents_legacy"
- source: "/leaderboard"
destination: "https://leaderboard.letta.com"
- source: "/leaderboard/overview"
destination: "https://leaderboard.letta.com"
- source: "/leaderboard/contributing"
destination: "https://leaderboard.letta.com"
- source: "/guides/agents/fetch-webpage"
destination: "/guides/agents/web-search"
Reference in New Issue View Git Blame Copy Permalink