120 lines
4.5 KiB
Plaintext
120 lines
4.5 KiB
Plaintext
---
|
|
title: "Honcho"
|
|
description: "Go beyond memory to agents with actual social intelligence"
|
|
icon: "brain"
|
|
sidebarTitle: "Overview"
|
|
---
|
|
|
|
Honcho is an AI-native memory library for building agents with
|
|
[state-of-the-art](https://blog.plasticlabs.ai/research/Introducing-Neuromancer-XR)
|
|
long-term memory.
|
|
|
|
Agents using Honcho have perfect recall with a wide variety of tools to traverse
|
|
their history and get the exact context they need when they need it.
|
|
|
|
It then goes beyond basic memory by reasoning about the stored history
|
|
to expand the latent information available to your agent. Agents using Honcho
|
|
will understand who they are, who they are interacting with, what happened, and
|
|
when it happened — all without you having to think about it.
|
|
|
|
Use it to build
|
|
|
|
- Highly personalized experiences
|
|
- Agents with social cognition
|
|
- Agents with rich identity that evolve over time
|
|
- Multi-agent systems with complex social dynamics
|
|
|
|
|
|
```python
|
|
# Start simple by just adding messages
|
|
session.add_messages([alice.message("I learn best with examples")])
|
|
|
|
# Honcho will automatically reason about the message to generate insights about Alice
|
|
|
|
# Get insights by chatting with the agent
|
|
insight = peer.chat("How should I explain this concept?")
|
|
# > "This user learns best through concrete examples..."
|
|
```
|
|
|
|
Designed for developers and agents alike:
|
|
- **Natural Language Queries**: Chat with Honcho in natural language via the [Dialectic API](../core-concepts/architecture#dialectic-api) to get insights about your users and agents
|
|
- **Automatic Context Management**: Smart conversation summaries to have infinite chats
|
|
- **Native multi-agent support**: Sessions can natively have as many participants as you need
|
|
- **Agent-first interfaces**: MCP connections and APIs designed for agents to consume and use as tools
|
|
- **Provider Agnostic**: Works with any LLM or Agent Framework
|
|
|
|
## How It Works
|
|
|
|
<Accordion title="High Level Diagram" defaultOpen="true">
|
|
<Frame>
|
|
<img src="/images/overview/honcho-overview.svg" alt="High Level Honcho Diagram" />
|
|
</Frame>
|
|
</Accordion>
|
|
|
|
At a high level Honcho works very simply:
|
|
|
|
1. Store messages sent by users and agents in Honcho
|
|
2. Honcho reasons about the messages to generate insights about each entity in
|
|
the system
|
|
3. At runtime your agents can leverage insights from Honcho to get the exact
|
|
context they need
|
|
|
|
There are several API endpoints to leverage the memory & insights in Honcho.
|
|
|
|
### Get Context
|
|
|
|
This is the easiest way to leverage Honcho. simply call get context and get the
|
|
most relevant information for your conversation. This endpoint is highly
|
|
customizable so you can specify parameters such as:
|
|
|
|
- A number of tokens you want
|
|
- An option to include summaries of the conversation
|
|
- An option to get a profile of a specific user (Peer Card & Representation)
|
|
|
|
### Search
|
|
|
|
This endpoint lets you search across Honcho for relevant messages using a
|
|
hybrid search strategy that combines full-text and semantic search.
|
|
|
|
You can optionally scope the endpoint to a specific workspace, peer, or session.
|
|
|
|
### Working Representation
|
|
|
|
This endpoint gives you a snapshot of a user or what we call a
|
|
**Representation**. Essentially, a list of explicit and deductive facts about
|
|
the user that are relevant to the current conversation.
|
|
|
|
Plug this into your prompt to get a quick overview of the user.
|
|
|
|
### Dialectic API
|
|
|
|
This endpoint lets you chat with Honcho about any entity in your system. Honcho
|
|
will leverage what it has remembered and learned about the entity to provide in-context actionable insights.
|
|
|
|
This is especially helpful when you want your agent to back-channel with Honcho to
|
|
change its behavior at runtime.
|
|
|
|
Example Queries:
|
|
- "What's the best way to explain technical concepts to this user?"
|
|
- "Is this user more task-oriented or relationship-oriented?"
|
|
- "What time of day is this user most engaged?"
|
|
- "How does this user prefer to receive feedback?"
|
|
- "What are this user's core values based on our conversations?"
|
|
|
|
|
|
## Getting Started
|
|
|
|
Ready to integrate Honcho into your application?
|
|
|
|
<CardGroup cols={2}> <Card title="Quickstart Guide" icon="rocket"
|
|
href="/v2/documentation/introduction/quickstart"> Get up and running with
|
|
Honcho in minutes </Card> <Card title="Core Concepts" icon="brain"
|
|
href="/v2/documentation/core-concepts/architecture"> Understand Honcho's
|
|
fundamental concepts </Card> </CardGroup>
|
|
|
|
## Community & Support
|
|
|
|
- **GitHub**: [plastic-labs/honcho](https://github.com/plastic-labs/honcho)
|
|
- **Discord**: [Join our community](http://discord.gg/plasticlabs)
|
|
- **Issues**: Report bugs and request features on GitHub
|