chore: in progress edits
This commit is contained in:
Vineeth Voruganti
parent
b7eee24565
commit
c026a4fb45
|
|
@ -3,9 +3,9 @@
|
|||
"theme": "mint",
|
||||
"name": "Honcho",
|
||||
"colors": {
|
||||
"primary": "#86BCF2",
|
||||
"primary": "#66AAFF",
|
||||
"dark": "#151E27",
|
||||
"light": "#B5D9FD"
|
||||
"light": "#86BCF2"
|
||||
},
|
||||
"favicon": "/favicon.svg",
|
||||
"contextual": {
|
||||
|
|
|
|||
|
|
@ -7,17 +7,15 @@ sidebarTitle: "Architecture"
|
|||
|
||||
<Note> The goal of this page is to build an intuition for the primitives in Honcho and how they fit together </Note>
|
||||
|
||||
Honcho has 3 main components that work together to manage agent identity and context.
|
||||
Honcho has 2 main components that work together to manage agent identity and context.
|
||||
|
||||
- **The Storage API**: The Memory layer for storing interaction history for your agents
|
||||
- **The Deriver**: The background processing layer that builds representations of users and agents
|
||||
- **The Dialectic API**: The natural language API for chatting with representations
|
||||
- **The Memory Layer**: The Memory layer for storing interaction history for your agents
|
||||
- **The Reasoning Layer**: The background processing layer that builds representations of users and agents
|
||||
|
||||
Below we'll deep dive into these different areas, discussing the data
|
||||
primitives, the flow of data through the system, artifacts Honcho produces, and
|
||||
how to use them.
|
||||
|
||||
|
||||
## Data Model
|
||||
|
||||
Honcho has a hierarchical data model centered around the entities below.
|
||||
|
|
@ -37,9 +35,9 @@ Honcho has a hierarchical data model centered around the entities below.
|
|||
style SM fill:#e8f5e9,stroke:#2e7d32,color:#000
|
||||
```
|
||||
|
||||
There are `Workspaces` at the top that contain `Peers` and `Sessions`. A `Peer`
|
||||
can be part of many `Sessions` and a `Session` can have many `Peers`. `Sessions`
|
||||
hold messages that are sent by `Peers`.
|
||||
A `Workspaces` has `Peers` & `Sessions`
|
||||
A `Peer` can be in multiple `Sessions` and a can send `Messages` in a `Session`.
|
||||
A `Session` can have many `Peers` and has `Messages` sent by `Peers`.
|
||||
|
||||
### <Icon icon="building" /> Workspaces
|
||||
|
||||
|
|
@ -126,19 +124,39 @@ with a single peer and structure the data as messages.
|
|||
- File uploads (PDFs, text files, JSON documents)
|
||||
|
||||
|
||||
## Deriver
|
||||
## Reasoning Layer
|
||||
|
||||
The raw data you store in Honcho is useful, but it's not in a format that's most
|
||||
useful for an LLM to consume. There may be too many tokens that need to be
|
||||
compacted, key facts about what happened may be hard to piece together because
|
||||
they involve messages from across different sessions, etc.
|
||||
|
||||
To solve this problem, Honcho has a reasoning layer that is always processing
|
||||
data that comes into Honcho to have the must informationaly dense and useful
|
||||
data that we can expose to agents. Currently, Honcho does the following tasks in
|
||||
the reasoning engine.
|
||||
|
||||
- **Fact Derivation**
|
||||
- **Generate Summaries**
|
||||
- **Generate Peer Cards**
|
||||
- **Dreaming**
|
||||
|
||||
|
||||
So Honcho will reason about each `Message` it
|
||||
ingests to generate new facts and insights that are spelled out and easy to
|
||||
consume in an LLM prompt.
|
||||
|
||||
We refer to this module of Honcho as the `Deriver`, because it constantly is
|
||||
deriving new insights from messages. The sum total of all these generated
|
||||
insights are what we refer to as a `Representation`, all the data related who
|
||||
and what a `Peer` is.
|
||||
|
||||
At the core of developing representations of Peers, we have the Deriver. The
|
||||
Deriver refers to a set of processes in Honcho that enqueue new messages sent
|
||||
by peers and reasons over them to extract facts, insights, and context.
|
||||
|
||||
Depending on the configuration of a `Peer` or `Session`, the deriver will behave
|
||||
differently and update different representations.
|
||||
|
||||
Facts derived here are used in the Dialectic chat endpoint to generate
|
||||
context-aware responses that can correctly reference both concrete facts
|
||||
extracted from messages and social insights deduced from facts, tone, and
|
||||
opinion.
|
||||
Facts derived here are used in the Dialectic chat endpoint, get_context
|
||||
endpoint,
|
||||
|
||||
<Info>
|
||||
Deriver tasks are processed in parallel, but tasks affecting the same peer representation will always be processed serially in order of message creation, so as to properly understand their cumulative effect.
|
||||
|
|
@ -149,7 +167,7 @@ There are two types of tasks that the deriver currently does:
|
|||
- **Representation Tasks**: Generate/update peer representations
|
||||
- **Summary Tasks**: Generate conversation summaries
|
||||
|
||||
### Peer Representations
|
||||
### Local & Global Representations
|
||||
|
||||
Peer representations are more of an abstract concept, as they are made up of
|
||||
various pieces of data stored throughout Honcho. There are however
|
||||
|
|
|
|||
|
|
@ -5,27 +5,20 @@ icon: "brain"
|
|||
sidebarTitle: "Overview"
|
||||
---
|
||||
|
||||
When building agents developers often run into the same walls:
|
||||
Honcho is an AI-native memory library for building agents with [state-of-the-art](https://blog.plasticlabs.ai/research/Introducing-Neuromancer-XR) memory.
|
||||
|
||||
> "My agent forgets everything between chats"
|
||||
It then goes beyond basic memory by reasoning about the stored data
|
||||
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.
|
||||
|
||||
You need memory: session management, message storage, context handling. It's table stakes, but surprisingly complex to get right.
|
||||
Use it to build
|
||||
|
||||
> "My agent treats everyone exactly the same"
|
||||
- Highly personalized experiences
|
||||
- Agents with social cognition
|
||||
- Agents with rich identity that evolve over time
|
||||
- Multi-agent systems with complex social dynamics
|
||||
|
||||
You need personalization: user modeling, preference learning, behavioral adaptation. Now you're building a [social cognition](../core-concepts/glossary#social-cognition) engine.
|
||||
|
||||
> "I'm writing infrastructure instead of features"
|
||||
|
||||
You need Honcho
|
||||
|
||||
<img src="/images/agent_hierarchy.png" alt="Honcho's Hiearchy of Agents" />
|
||||
|
||||
Honcho delivers production-ready memory infrastructure from day one. Store
|
||||
conversations, manage sessions, get perfectly formatted context for any LLM.
|
||||
But here's the magic: while your agents are chatting, Honcho is learning. It
|
||||
builds Theory of Mind models automatically, transforming raw conversations into
|
||||
rich psychological understanding.
|
||||
|
||||
```python
|
||||
# Start simple - just add messages
|
||||
|
|
@ -52,27 +45,22 @@ Designed for developers and agents alike:
|
|||
Developers use Honcho to store information about their users and application via
|
||||
two integrated layers:
|
||||
|
||||
<img src="/images/basic_honcho_flowchart.png" alt="Basic Honcho Flowchart" />
|
||||
|
||||
**Memory Layer**: Captures all user interactions - messages, preferences, and
|
||||
behavioral patterns - in a peer-centric data model that scales from individual
|
||||
conversations to complex multi-agent scenarios. This also queues up messages for
|
||||
the reasoning layer to process.
|
||||
|
||||
**Reasoning Layer**: Continuously analyzes stored interactions to build
|
||||
psychological profiles using [theory of mind](../core-concepts/glossary#theory-of-mind)
|
||||
inference, extracting patterns about communication style, decision-making
|
||||
preferences, and mental models.
|
||||
**Reasoning Layer**: Continuously analyzes stored interactions to improve the
|
||||
memories and representation of each `Peer` in the system.
|
||||
|
||||
### Retrieval
|
||||
|
||||
Once data is stored and generated within Honcho, the API exposes several
|
||||
different ways to retrieve and use those insights.
|
||||
|
||||
**[Dialectic API](/v2/guides/dialectic-endpoint)**: This is the
|
||||
flagship endpoint that allows developers to send natural language queries to
|
||||
Honcho to chat with the representation of each user in your system to get
|
||||
dynamic, in-context actionable insights.
|
||||
**[Dialectic API](/v2/guides/dialectic-endpoint)**: This is the flagship
|
||||
endpoint that allows developers chat with Honcho about any aspect of each user
|
||||
in your system to get dynamic, in-context actionable insights.
|
||||
|
||||
Example Queries
|
||||
- "What's the best way to explain technical concepts to this user?"
|
||||
|
|
|
|||
Loading…
Reference in New Issue