AI agent & LLM app platform
How to install typedai?
trafficguard/typedai
$git clone https://github.com/trafficguard/typedaiInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install typedai by running `git clone https://github.com/trafficguard/typedai`, then use it for the current task and follow its documentation at https://github.com/trafficguard/typedai.
README.md
| 1 | <a id="banner"></a> |
| 2 | <p align="center"> |
| 3 | <img src="https://public.trafficguard.ai/typedai/banner.png" alt="TypedAI banner"/> |
| 4 | </p> |
| 5 | <p align="center"> |
| 6 | <em >The TypeScript-first AI platform for developers</em><br/> |
| 7 | <small>Autonomous AI agents and LLM based workflows</small> |
| 8 | </p> |
| 9 | |
| 10 | ## Documentation site |
| 11 | [Home](https://typedai.dev/) | [Setup](https://typedai.dev/setup/) | [Observability](https://typedai.dev/observability/) | [Function calling](https://typedai.dev/functions/) | |
| 12 | [Autonomous AI Agent](https://typedai.dev/autonomous-agents/) | [AI Software Engineer](https://typedai.dev/software-engineer/) | [AI Code reviews](https://typedai.dev/code-review/) | |
| 13 | [Tools/Integrations](https://typedai.dev/integrations/) | [Roadmap](https://typedai.dev/roadmap/) |
| 14 | |
| 15 | --- |
| 16 | |
| 17 | [Features](#key-features) | [UI Examples](#ui-examples) | [Code examples](#code-examples) | [Contributing](#contributing) |
| 18 | |
| 19 | TypedAI is a full-featured platform for developing and running agents, LLM based workflows and chatbots. |
| 20 | |
| 21 | Included are capable software engineering agents, which have assisted building the platform. |
| 22 | |
| 23 | ## Key features |
| 24 | |
| 25 | - [Advanced Autonomous agents](https://typedai.dev/autonomous-agents) |
| 26 | - [Software developer agents](https://typedai.dev/software-engineer/) |
| 27 | - [Pull request code review agent](https://typedai.dev/code-review/) |
| 28 | - [AI chat interface](https://typedai.dev/chat/) |
| 29 | - [Slack chatbot](https://typedai.dev/chatbot/) |
| 30 | - Supports many LLM services - OpenAI, Anthropic (native & Vertex), Gemini, Groq, Fireworks, Together.ai, DeepSeek, Ollama, Cerebras, SambaNova, OpenRouter, X.ai |
| 31 | - Multi-agent [extend-reasoning implementations](https://github.com/TrafficGuard/typedai/tree/main/src/llm/multi-agent) of the LLM interface |
| 32 | - Configurable Human-in-the-loop settings |
| 33 | - [Functional callable tools/integrations](https://typedai.dev/integrations/) (Filesystem, Jira, Slack, Perplexity, Google Cloud, Gitlab, GitHub etc) |
| 34 | - CLI and Web UI interface |
| 35 | - Run locally or deployed on the cloud with multi-user/SSO |
| 36 | - OpenTelemetry based observability |
| 37 | - Leverages the extensive Python AI ecosystem through executing Python scripts/packages |
| 38 | |
| 39 | ## CLI Usage |
| 40 | |
| 41 | TypedAI provides powerful command-line tools for automation and development workflows: |
| 42 | |
| 43 | ```bash |
| 44 | # Quick examples using the ai wrapper script |
| 45 | ai query "What test frameworks does this repository use?" |
| 46 | ai code "Add error handling to the user authentication function" |
| 47 | ai research "Latest developments in large language models" |
| 48 | ``` |
| 49 | |
| 50 | The `ai` script runs locally while `aid` runs in Docker for isolation. Both provide access to all CLI agents including the specialized `codeAgent` for autonomous code editing tasks. |
| 51 | |
| 52 | For comprehensive CLI documentation, see the [CLI Usage Guide](https://typedai.dev/cli-usage/). |
| 53 | |
| 54 | ## Autonomous agents |
| 55 | |
| 56 | - Reasoning/planning inspired from Google's [Self-Discover](https://arxiv.org/abs/2402.03620) and other papers |
| 57 | - Memory and function call history for complex workflows |
| 58 | - Iterative planning with hierarchical task decomposition |
| 59 | - Sandboxed execution of generated code for multi-step function calling and logic |
| 60 | - LLM function schemas auto-generated from source code |
| 61 | - Human-in-the-loop for budget control, agent initiated questions and error handling |
| 62 | |
| 63 | More details at the [Autonomous agent docs](https://typedai.dev/autonomous-agents) |
| 64 | |
| 65 | ## Software developer agents |
| 66 | |
| 67 | - Code Editing Agent for local repositories |
| 68 | - Auto-detection of project initialization, compile, test and lint |
| 69 | - Task file selection agent selects the relevant files |
| 70 | - Design agent creates the implementation plan. |
| 71 | - Code editing loop with compile, lint, test, fix |
| 72 | - Compile error analyser can search online, add additional files and install packages |
| 73 | - Final review of the changes with an additional code editing loop if required. |
| 74 | - Software Engineer Agent (For ticket to Pull Request workflow): |
| 75 | - Find the appropriate repository from GitLab/GitHub |
| 76 | - Clone and create branch |
| 77 | - Call the Code Editing Agent |
| 78 | - Create merge request |
| 79 | - Code Review agent: |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
