diff --git a/docs/v3/documentation/features/advanced/overview.mdx b/docs/v3/documentation/features/advanced/overview.mdx index 00a92cc2..77f17a7b 100644 --- a/docs/v3/documentation/features/advanced/overview.mdx +++ b/docs/v3/documentation/features/advanced/overview.mdx @@ -10,7 +10,7 @@ Advanced features give you fine-grained control over Honcho's behavior and imple ## Configuration & Monitoring - [Queue Status](/v3/documentation/features/advanced/queue-status) - Monitor background processing and reasoning tasks -- [Configuration](/v3/documentation/features/advanced/toggle-reasoning) - Configure reasoning models and behavior +- [Configuration](/v3/documentation/features/advanced/reasoning-configuration) - Configure reasoning models and behavior - [Summarizer](/v3/documentation/features/advanced/summarizer) - Automatic session summarization ## Querying & Filtering diff --git a/docs/v3/documentation/introduction/vibecoding.mdx b/docs/v3/documentation/introduction/vibecoding.mdx index 40a2d0c2..43679935 100644 --- a/docs/v3/documentation/introduction/vibecoding.mdx +++ b/docs/v3/documentation/introduction/vibecoding.mdx @@ -1,7 +1,7 @@ --- title: "AI-Powered Honcho Setup" icon: "wand-magic-sparkles" -description: "Universal starter prompt and Claude Code skill for building with Honcho" +description: "Agent skills and starter prompt for building with Honcho" sidebarTitle: 'Vibecoding Setup' --- @@ -14,38 +14,44 @@ We follow the llms.txt standard. There are both an llms.txt and llms-full.txt av --- -## Claude Code Skill +## Agent Skills -If you're using [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview), you can install the Honcho integration skill for a guided, interactive setup experience. The skill will explore your codebase, ask targeted questions about your integration needs, and implement Honcho step by step. - -### Installation +We provide agent skills for coding assistants like Claude Code, Cursor, Windsurf, and others. -```bash Global Installation (all projects) -# Add to your global skills directory -curl -o ~/.claude/skills/honcho-integration.md https://raw.githubusercontent.com/plastic-labs/honcho/main/docs/SKILL.md +```bash Install via npx (Recommended) +npx skills add plastic-labs/honcho ``` -```bash Project-specific Installation -# Add to your project's .claude directory -mkdir -p .claude/skills -curl -o .claude/skills/honcho-integration.md https://raw.githubusercontent.com/plastic-labs/honcho/main/docs/SKILL.md +```bash Install as Claude Skill Manually +curl -o ~/.claude/skills/honcho-integration.md https://raw.githubusercontent.com/plastic-labs/honcho/main/docs/SKILL.md ``` -### Usage +### Available Skills -Once installed, invoke the skill in Claude Code: +#### honcho-integration -``` -/honcho-integration -``` +**For new integrations.** This skill helps you add Honcho to an existing Python or TypeScript codebase. It provides a guided, interactive experience: -The skill will: -1. **Explore your codebase** to understand your language, framework, and existing AI/LLM integrations -2. **Interview you** about which entities should be peers, your preferred integration pattern, and session structure -3. **Implement the integration** based on your answers -4. **Verify the setup** to ensure everything is configured correctly +1. **Explores your codebase** to understand your language, framework, and existing AI/LLM integrations +2. **Interviews you** about which entities should be peers, your preferred integration pattern, and session structure +3. **Implements the integration** based on your answers—installing the SDK, creating peers, configuring sessions, and wiring up the chat endpoint +4. **Verifies the setup** to ensure everything is configured correctly + +Invoke with `/honcho-integration` in your coding agent. + +#### migrate-honcho-py / migrate-honcho-ts + +**For SDK upgrades.** Migrates code from v1.6.0 to v2.0.0 (required for Honcho 3.0.0). Use when upgrading the SDK or seeing errors about removed APIs like `observations`, `Representation`, `.core`, or `get_config`. + +Both skills handle: terminology changes (`Observation` → `Conclusion`), `Representation` class removal, method renames, and streaming API updates. + +| Python | TypeScript | +|--------|------------| +| `/migrate-honcho-py` | `/migrate-honcho-ts` | +| `AsyncHoncho` → `.aio` accessor | `@honcho-ai/core` removal | +| | `snake_case` → `camelCase` | --- diff --git a/docs/v3/documentation/reference/sdk.mdx b/docs/v3/documentation/reference/sdk.mdx index 05b0daf6..9e0ce05d 100644 --- a/docs/v3/documentation/reference/sdk.mdx +++ b/docs/v3/documentation/reference/sdk.mdx @@ -879,7 +879,7 @@ If `created_at` is not provided, messages will use the server's current timestam ### Metadata and Filtering -See [Using Filters](/v3/guides/using-filters) for more examples on how to use filters. +See [Using Filters](/v3/documentation/features/advanced/using-filters) for more examples on how to use filters. ```python Python diff --git a/docs/v3/documentation/scratch/honcho-memory/quickstart.mdx b/docs/v3/documentation/scratch/honcho-memory/quickstart.mdx index a8953fdc..df7fabae 100644 --- a/docs/v3/documentation/scratch/honcho-memory/quickstart.mdx +++ b/docs/v3/documentation/scratch/honcho-memory/quickstart.mdx @@ -237,7 +237,7 @@ and Bob. We: 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](/v3/documentation/core-concepts/configuration). +behavior and can be toggled off via [the configuration](/v3/documentation/features/advanced/reasoning-configuration). ## Next Steps diff --git a/docs/v3/documentation/scratch/local-vs-global.mdx b/docs/v3/documentation/scratch/local-vs-global.mdx index 29674d57..e46f2b80 100644 --- a/docs/v3/documentation/scratch/local-vs-global.mdx +++ b/docs/v3/documentation/scratch/local-vs-global.mdx @@ -53,7 +53,7 @@ This feature is illustrated in the graphic below: We can enable local representation for a `Peer` by setting `observe_others=True`. This is shown in the [Configure -Reasoning](/v3/documentation/core-concepts/configuration) page. +Reasoning](/v3/documentation/features/advanced/reasoning-configuration) page. Now if we used Bob's local representation of Alice then Bob would only get insights on what they've seen Alice say to them. diff --git a/docs/v3/guides/integrations/crewai.mdx b/docs/v3/guides/integrations/crewai.mdx index 57fda576..4c9185c1 100644 --- a/docs/v3/guides/integrations/crewai.mdx +++ b/docs/v3/guides/integrations/crewai.mdx @@ -97,7 +97,7 @@ results = storage.search("query", filters={ }) ``` -For the full filter syntax including logical operators (AND, OR, NOT), comparison operators, and metadata filtering, see the [Using Filters](https://docs.honcho.dev/v3/documentation/core-concepts/features/using-filters) documentation. +For the full filter syntax including logical operators (AND, OR, NOT), comparison operators, and metadata filtering, see the [Using Filters](https://docs.honcho.dev/v3/documentation/features/advanced/using-filters) documentation. For comprehensive details about CrewAI's memory system, see the [official CrewAI Memory documentation](https://docs.crewai.com/en/concepts/memory). @@ -282,13 +282,13 @@ Now that you have a working CrewAI integration with Honcho, you can: Understand Honcho's peer-based model and core primitives - + Learn about retrieving and formatting conversation context - + Query `peer` representations for deeper understanding - + Build stateful agents with LangGraph and Honcho diff --git a/docs/v3/guides/integrations/langgraph.mdx b/docs/v3/guides/integrations/langgraph.mdx index 5427e24f..59781c98 100644 --- a/docs/v3/guides/integrations/langgraph.mdx +++ b/docs/v3/guides/integrations/langgraph.mdx @@ -227,7 +227,7 @@ const graph = new StateGraph(StateAnnotation) ### Understanding get_context() -The [`get_context()`](/v3/documentation/core-concepts/features/get-context) method retrieves comprehensive conversation context and formats it for your LLM. It automatically: +The [`get_context()`](/v3/documentation/features/get-context) method retrieves comprehensive conversation context and formats it for your LLM. It automatically: - **Manages conversation history** - Tracks all messages and determines what's relevant - **Respects token limits** - Stays within context window constraints without manual counting @@ -248,7 +248,7 @@ That's it. Call `session.get_context().to_openai(assistant)` and you get properl -For more details on all available parameters, see [`get_context() documentation`](/v3/documentation/core-concepts/features/get-context) +For more details on all available parameters, see [`get_context() documentation`](/v3/documentation/features/get-context) ## Chat Loop @@ -354,10 +354,10 @@ Now that you have a working LangGraph integration with Honcho, you can: ## Related Resources - + Learn more about retrieving and formatting conversation context - + Use Honcho in Claude Desktop with MCP diff --git a/docs/v3/guides/migrations/mem0.mdx b/docs/v3/guides/migrations/mem0.mdx index 77022854..79893bd4 100644 --- a/docs/v3/guides/migrations/mem0.mdx +++ b/docs/v3/guides/migrations/mem0.mdx @@ -259,14 +259,14 @@ Reference the [API Comparison](#api-comparison) to replace your Mem0 API calls w Mem0 requires manual assembly of context from `search()` results. Honcho's `session.get_context()` returns a ready-to-use `SessionContext` object with built-in token limits, auto-included summaries, and format helpers (`.to_openai()`, `.to_anthropic()`). - + Learn more about token-optimized context retrieval Mem0's `search()` returns basic vector, semantic, or raw memory matches. Honcho's `peer.chat()` enables your agent to *reason* about what it knows—returning synthesized natural language insights with streaming support and scoped queries. - + Learn more about inference-powered queries @@ -285,7 +285,7 @@ Additional features with **no Mem0 equivalent**: Understand peers and sessions - + Inference responses diff --git a/docs/v3/guides/overview.mdx b/docs/v3/guides/overview.mdx index 9b39510f..a74d66c3 100644 --- a/docs/v3/guides/overview.mdx +++ b/docs/v3/guides/overview.mdx @@ -16,10 +16,10 @@ Each guide focuses on a specific use case with practical examples. The goal is t Quick integration guides to get up and running: - + Get Honcho running with a single prompt in Claude Code - + Add persistent memory and theory of mind to your LangGraph agents diff --git a/docs/v3/guides/storing-data.mdx b/docs/v3/guides/storing-data.mdx index 961b9e1f..a1085668 100644 --- a/docs/v3/guides/storing-data.mdx +++ b/docs/v3/guides/storing-data.mdx @@ -42,7 +42,7 @@ Once a `Message` is saved in Honcho, it will kick off a background task that looks at the new data to generate insights about the `Peer` that sent the `Message` This is the default behavior of Honcho and can be turned off by [configuring the -Peer or Session](/v3/documentation/core-concepts/configuration) +Peer or Session](/v3/documentation/features/advanced/reasoning-configuration) This pattern of having a Peer, Session, and Messages is highly flexible and works for many different use cases and agent setups. Some use cases may only diff --git a/docs/v3/migrations/from-mem0.mdx b/docs/v3/migrations/from-mem0.mdx index 77022854..79893bd4 100644 --- a/docs/v3/migrations/from-mem0.mdx +++ b/docs/v3/migrations/from-mem0.mdx @@ -259,14 +259,14 @@ Reference the [API Comparison](#api-comparison) to replace your Mem0 API calls w Mem0 requires manual assembly of context from `search()` results. Honcho's `session.get_context()` returns a ready-to-use `SessionContext` object with built-in token limits, auto-included summaries, and format helpers (`.to_openai()`, `.to_anthropic()`). - + Learn more about token-optimized context retrieval Mem0's `search()` returns basic vector, semantic, or raw memory matches. Honcho's `peer.chat()` enables your agent to *reason* about what it knows—returning synthesized natural language insights with streaming support and scoped queries. - + Learn more about inference-powered queries @@ -285,7 +285,7 @@ Additional features with **no Mem0 equivalent**: Understand peers and sessions - + Inference responses