diff --git a/docs/v2/documentation/core-concepts/configuration.mdx b/docs/v2/documentation/core-concepts/configuration.mdx index ced19fe7..bc8635b9 100644 --- a/docs/v2/documentation/core-concepts/configuration.mdx +++ b/docs/v2/documentation/core-concepts/configuration.mdx @@ -1,5 +1,5 @@ --- -title: 'Configure Peers' +title: 'Configure Reasoning' description: 'Customizing how Honcho handles peers and sessions' icon: 'wrench' --- diff --git a/docs/v2/documentation/introduction/overview.mdx b/docs/v2/documentation/introduction/overview.mdx index ed2eddad..254f6512 100644 --- a/docs/v2/documentation/introduction/overview.mdx +++ b/docs/v2/documentation/introduction/overview.mdx @@ -10,9 +10,9 @@ Honcho is an AI-native memory library for building agents with long-term memory. Agents using Honcho have perfect recall with a wide variety of tools to traverse -the history of an agent and get the exact context they need when they need it. +their history and get the exact context they need when they need it. -It then goes beyond basic memory by reasoning about the stored messages +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. @@ -26,11 +26,10 @@ Use it to build ```python -# Start simple - just add messages +# 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 +# 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?") @@ -38,22 +37,20 @@ insight = peer.chat("How should I explain this concept?") ``` Designed for developers and agents alike: -- **Natural Language Queries**: Chat with Honcho in natural language via the [Dialectic API](../core-concepts/architecture#dialectic-api) and let agents backchannel -- **Automatic Context Management**: Smart summarization that respects token limits -- **Native multi-agent support**: Break out of User/Assistant Paradigms and build complex multi-agent systems +- **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 chates +- **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 - -High Level Honcho Diagram - - + + High Level Honcho Diagram + - At a high level Honcho works very simply: 1. Store messages sent by users and agents in Honcho @@ -68,7 +65,7 @@ There are several API endpoints to leverage the memory & insights in Honcho. 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 +customizable so you can specify parameters such as: - A number of tokens you want - An option to include summaries of the conversation @@ -76,8 +73,8 @@ customizable so you can specify ### Search -This endpoint lets you search across Honcho for relevant messages either using a -hybrid search strategy that combines text search and cosine similarity. +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. @@ -97,7 +94,7 @@ will leverage what it has remembered and learned about the entity to provide in- This comes in handy when you want your agent to back-channel with Honcho to change it's behavior at runtime. -Example Queries +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?" @@ -112,7 +109,7 @@ Ready to integrate Honcho into your application? Get up and running with Honcho in minutes Understand Honcho's +href="/v2/documentation/core-concepts/architecture"> Understand Honcho's fundamental concepts ## Community & Support diff --git a/docs/v2/documentation/introduction/quickstart.mdx b/docs/v2/documentation/introduction/quickstart.mdx index 30175b5e..3777c1a4 100644 --- a/docs/v2/documentation/introduction/quickstart.mdx +++ b/docs/v2/documentation/introduction/quickstart.mdx @@ -62,7 +62,7 @@ The Honcho client is the main entry point for interacting with Honcho's API. By from honcho import Honcho # Initialize client (uses demo environment and default workspace) -client = Honcho() +honcho = Honcho() ``` @@ -70,7 +70,7 @@ client = Honcho() import { Honcho } from '@honcho-ai/sdk'; // Initialize client (uses demo environment and default workspace) -const client = new Honcho({}); +const honcho = new Honcho({}); ``` @@ -83,7 +83,7 @@ import os from honcho import Honcho # Production environment with API key -client = Honcho( +honcho = Honcho( api_key=os.environ["HONCHO_API_KEY"], environment="production", # Create a workspace, otherwise set to "default" @@ -95,7 +95,7 @@ client = Honcho( import { Honcho } from '@honcho-ai/sdk'; // Production environment with API key -const client = new Honcho({ +const honcho = new Honcho({ apiKey: process.env.HONCHO_API_KEY!, environment: "production", // Create a workspace, otherwise set to "default" @@ -110,13 +110,13 @@ Peers represent individual users, AI agents, or any conversational entity in you ```python Python -alice = client.peer("alice") -bob = client.peer("bob") +alice = honcho.peer("alice") +bob = honcho.peer("bob") ``` ```typescript TypeScript -const alice = await client.peer("alice") -const bob = await client.peer("bob") +const alice = await honcho.peer("alice") +const bob = await honcho.peer("bob") ``` @@ -126,12 +126,12 @@ Sessions are independent conversations that can include multiple peers: ```python Python -session = client.session("session_1") +session = honcho.session("session_1") session.add_peers([alice, bob]) ``` ```typescript TypeScript -const session = await client.session("session_1") +const session = await honcho.session("session_1") await session.addPeers([alice, bob]) ``` @@ -171,7 +171,7 @@ Now ask Honcho what it's learned - this is where the magic happens: ```python Python # Ask what Bob is like -response = alice.chat("Tell me about Bob's interests and habits") +response = bob.chat("Tell me about Bob's interests and habits") print(response) # Returns rich context like: @@ -182,36 +182,128 @@ print(response) ``` ```typescript TypeScript -(async () => { - // Ask what Bob is like - const response = await alice.chat("Tell me about Bob's interests and habits"); - console.log(response); +bob.chat("Tell me about Bob's interests and habits").then((response) => { + console.log(response); + // Returns rich context like: + // "Bob is health-conscious and has been working on getting back in shape. + // He regularly goes to the gym, particularly in the evenings, and finds + // exercise helps him relax. He's encouraging about fitness and willing + // to share advice about workout routines." +}) +``` + - // Returns rich context like: - // "Bob is health-conscious and has been working on getting back in shape. - // He regularly goes to the gym, particularly in the evenings, and finds - // exercise helps him relax. He's encouraging about fitness and willing - // to share advice about workout routines." -})(); +## 7. Putting it all together + + +```python Python +import os +from honcho import Honcho + +# Create your client +honcho = Honcho( + api_key=os.environ["HONCHO_API_KEY"], + environment="production", + # Create a workspace, otherwise set to "default" + # workspaceId="your-workspace-id" +) + +# Get your Peers +alice = honcho.peer("alice") +bob = honcho.peer("bob") + +# Make a Session and add your Peers +session = honcho.session("session_1") +session.add_peers([alice, bob]) + +# Add messages sent by your Peers +session.add_messages([ + alice.message("Hi Bob, how are you?"), + bob.message("I'm good, thank you!"), + alice.message("What are you doing today after work?"), + bob.message("I'm going to the gym! I've been trying to get back in shape."), + alice.message("That's great! I should probably start exercising too."), + bob.message("You should! I find that evening workouts help me relax."), +]) + +# Get insights about your Peers +response = bob.chat("Tell me about Bob's interests and habits") +print(response) + +# Returns rich context like: +# "Bob is health-conscious and has been working on getting back in shape. +# He regularly goes to the gym, particularly in the evenings, and finds +# exercise helps him relax. He's encouraging about fitness and willing +# to share advice about workout routines." +``` + +```typescript TypeScript +import { Honcho } from '@honcho-ai/sdk'; + +// Create your client +const honcho = new Honcho({ + apiKey: process.env.HONCHO_API_KEY!, + environment: "production", + // Create a workspace, otherwise set to "default" + // workspace: "your-workspace-id" +}); + +// Get your Peers +const alice = await client.peer("alice") +const bob = await client.peer("bob") + +// Make a Session and add your peers +const session = await client.session("session_1") +await session.addPeers([alice, bob]) + +// Add messages sent by your Peers +await session.addMessages([ + alice.message("Hi Bob, how are you?"), + bob.message("I'm good, thank you!"), + alice.message("What are you doing today after work?"), + bob.message("I'm going to the gym! I've been trying to get back in shape."), + alice.message("That's great! I should probably start exercising too."), + bob.message("You should! I find that evening workouts help me relax."), +]) + +// Get insights about your peers +bob.chat("Tell me about Bob's interests and habits").then((response) => { + console.log(response); + // Returns rich context like: + // "Bob is health-conscious and has been working on getting back in shape. + // He regularly goes to the gym, particularly in the evenings, and finds + // exercise helps him relax. He's encouraging about fitness and willing + // to share advice about workout routines." +}) ``` ## What Just Happened? -Honcho automatically built rich psychological profiles from just a few messages: +You just got through building a simple conversation between two people, Alice +and Bob. We: -- **Theory of Mind Processing**: Understanding personality, preferences, and patterns -- **Ambient Learning**: No surveys or explicit training - just natural conversation -- **Rich Context**: Far more detailed than simple conversation history +1. Set up our connection to Honcho. +2. Setup who the participants of our conversation are, these are called `Peers`. +3. Made a `Session` and added our `Peers` to it. +4. Sent messages from our `Peers` +5. Chat with Honcho to get insights about one of the `Peers` in the conversation -The response isn't just retrieving stored text - it's synthesizing insights about Bob's personality, habits, and communication style. +As soon as you save a message in Honcho, it will start to reason about it to +pull out insights and develop a profile of the user. This is the default +behavior and can be toggled off via [the configuration](/v2/documentation/core-concepts/configuration). ## Next Steps -This covers the core concepts: **peers**, **sessions**, **messages**, and **dialectic queries**. - -- For production use, [sign up for the managed platform](https://app.honcho.dev) or get an [overview here](../reference/platform). -- For detailed API reference, check out our [SDK documentation](../reference/sdk). -- For more examples, explore our [guides](../guides/overview). - ---- + + + Learn about the data primitives in Honcho and how they work together + + + Sign up for Managed Honcho and get started building agents now. + + + Check out spellbooks to see different examples apps built with Honcho + + diff --git a/docs/v2/documentation/introduction/vibecoding.mdx b/docs/v2/documentation/introduction/vibecoding.mdx index 31f98ff6..aae55775 100644 --- a/docs/v2/documentation/introduction/vibecoding.mdx +++ b/docs/v2/documentation/introduction/vibecoding.mdx @@ -5,7 +5,17 @@ description: "Universal starter prompt for building with Honcho" sidebarTitle: 'Vibecoding Setup' --- -Copy this prompt into Cursor, Claude, or any AI coding assistant to start building with Honcho. +These docs are designed to be easily consumable for LLMs. each page has a button +the lets you copy the page as markdown or put directly into ChatGPT or Claude. + +Additionally, we follow the llms.txt standard. There is both an llms.txt and +llms-full.txt available. + +- [llms.txt](/llms.txt) +- [llms-full.txt](/llms-full.txt) + +Additionally, we provide a starter prompt to paste into a coding assistant to +quickly get started building with Honcho. ## 🚀 Universal Starter Prompt