# AI Agent

Agent threads, tools and streaming

- Package: @bijectionhq/agents
- Category: AI & Agents
- Status: Included
- License: Apache-2.0
- Bijection source (repository access required): https://github.com/bijectionhq/agents/tree/8598acb6eeab2b2f76ac99feb4abcc3e66602de9
- Upstream: https://github.com/convex/agent/tree/d143f27c0dc1ce7269db38cf8d450e85a39e186f
- Documentation: https://docs.bijection.com/components/using
- Directory: https://bijection.com/components/agents

## Get the source

Bijection repository access is required. Request access at https://bijection.com/contact.

```sh
git clone https://github.com/bijectionhq/agents.git
cd agents
git checkout 8598acb6eeab2b2f76ac99feb4abcc3e66602de9
```

## Before using this component

Read the package README at the recorded revision for setup, dependencies, and API examples. Upstream documentation describes the original package and may differ from the Bijection adaptation. This source is included in Bijection's workspace. Catalog inclusion does not establish npm availability or runtime qualification. Check compatibility with your SDK and deployment before adoption. External providers run their own compute.

## Upstream package documentation

Recorded 2026-10-23. This describes @convex-dev/agent; check the Bijection adaptation separately.

The AI Agent component provides a structured framework for building agentic AI workflows with persistent message threads, automatic conversation context, and vector search capabilities. It separates long-running AI operations from your UI while maintaining real-time reactivity through Convex's websocket streaming. The component handles thread management, message persistence, file storage integration, and includes built-in debugging tools and usage tracking.

### Use cases

- Building customer support chatbots that need to maintain conversation history across multiple sessions and agents
- Creating multi-step AI workflows where different agents handle specific tasks like research, analysis, and reporting
- Implementing collaborative AI assistants where human agents and AI agents work together in shared threads
- Developing AI-powered applications that require RAG capabilities with hybrid vector and text search across conversation history
- Building usage-metered AI services that need per-user, per-agent cost tracking and rate limiting

### How it works

The component centers around Agents, Threads, and Messages as core abstractions. Agents encapsulate LLM prompting logic, tools, and behavior, while Threads persist conversation history that can be shared across multiple users and agents. Messages automatically include conversation context through built-in hybrid vector/text search within threads.

Streaming is handled through Convex's websocket infrastructure, enabling real-time text and object streaming without HTTP streaming complications. The component integrates with Convex file storage for automatic file handling with reference counting, and supports both static and dynamic workflows for complex multi-agent operations.

Debugging capabilities include callback functions, an agent playground for prompt iteration, and dashboard inspection. Usage tracking provides granular metrics per-provider, per-model, and per-user, while rate limiting integration helps manage API costs and provider limits.

### Upstream README

AI Agents, built on Convex.
[Check out the docs here](https://docs.convex.dev/agents).

The Agent component manages threads and messages that agents can use in static
or dynamic workflows.

- [Agents](https://docs.convex.dev/agents/agent-usage) provide an abstraction
  for using LLMs to represent units of use-case-specific prompting with
  associated models, prompts,
  [Tool Calls](https://docs.convex.dev/agents/tools), and behavior in relation
  to other Agents, functions, APIs, and more.
- [Threads](https://docs.convex.dev/agents/threads) persist
  [messages](https://docs.convex.dev/agents/messages) and can be shared by
  multiple users and agents (including
  [human agents](https://docs.convex.dev/agents/human-agents)).
- Streaming text and objects using deltas over websockets so all clients stay in
  sync efficiently, without http streaming. Enables streaming from async
  functions.
- [Conversation context](https://docs.convex.dev/agents/context) is
  automatically included in each LLM call, including built-in hybrid vector/text
  search for messages in the thread and opt-in search for messages from other
  threads (for the same specified user).
- [RAG](https://docs.convex.dev/agents/rag) techniques are supported for prompt
  augmentation from other sources, either up front in the prompt or as tool
  calls. Integrates with the
  [RAG Component](https://www.convex.dev/components/rag), or DIY.
- [Workflows](https://docs.convex.dev/agents/workflows) allow building
  multi-step operations that can span agents, users, durably and reliably.
- [Files](https://docs.convex.dev/agents/files) are supported in thread history
  with automatic saving to [file storage](https://docs.convex.dev/file-storage)
  and ref-counting.
- [Debugging](https://docs.convex.dev/agents/debugging) is enabled by callbacks,
  the [agent playground](https://docs.convex.dev/agents/playground) where you
  can inspect all metadata and iterate on prompts and context settings, and
  inspection in the dashboard.
- [Usage tracking](https://docs.convex.dev/agents/usage-tracking) is easy to set
  up, enabling usage attribution per-provider, per-model, per-user, per-agent,
  for billing & more.
- [Rate limiting](https://docs.convex.dev/agents/rate-limiting), powered by the
  [Rate Limiter Component](https://www.convex.dev/components/rate-limiter),
  helps control the rate at which users can interact with agents and keep you
  from exceeding your LLM provider's limits.

[Read the associated Stack post here](https://stack.convex.dev/ai-agents).

[![Powerful AI Apps Made Easy with the Agent Component](https://thumbs.video-to-markdown.com/b323ac24.jpg)](https://youtu.be/tUKMPUlOCHY)
**Read the [docs](https://docs.convex.dev/agents) for more details.**

Play with the example:

```sh
git clone https://github.com/convex/agent.git
cd agent
npm run setup
npm run dev
```

Found a bug? Feature request?
[File it here](https://github.com/convex/agent/issues).