Search

More Filters

Show More
Add Listing
Go Back

agentica

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Agentica is an open source AI function calling framework designed to let developers convert TypeScript functions, OpenAPI/Swagger documents, or an MCP (Model Context Protocol) server into working AI agents. Its primary purpose is to remove the manual work and instability around LLM function calling by automatically building and managing function schemas, handling vendor differences in JSON Schema and OpenAPI, and providing tooling to expose functions as agent controllers. The project targets TypeScript and backend developers and supplies a CLI setup wizard to scaffold projects, a WebSocket protocol for non-standalone server projects, and an interactive playground for demos. Agentica emphasizes compiler-driven generation of schemas, validation feedback to detect and correct argument mistakes, and a selector agent for filtering candidate functions so agents are efficient and reliable. The repository includes documentation, tutorials, and examples showing how to wire OpenAI and other vendors to controllers for tasks like e-commerce or content retrieval.

Links

Stars
903
App URL
https://github.com/wrtnlabs/agentica
Github Repository
https://github.com/wrtnlabs/agentica/blob/main/README.md

Categorization

App Details

Features
Agentica bundles features aimed at stabilizing and simplifying AI function calling. It offers compiler-driven development that generates function-calling schemas automatically from TypeScript. It includes conversion and emendation utilities to handle JSON Schema and OpenAPI variability across vendors. Validation feedback inspects and corrects malformed arguments produced by LLMs. A selector agent filters and prioritizes candidate functions to reduce context size and token usage. Integration paths include TypeScript class controllers, assertHttpController for OpenAPI/Swagger endpoints, and MCP server support. There is a CLI setup wizard to scaffold projects, an interactive playground showcasing TypeScript, OpenAPI, and enterprise demos, and documentation with tutorials and API references. The codebase is vendor-agnostic and lists compatible LLMs and schema targets. The project is distributed under the MIT license and maintained with examples and community support channels.
Use Cases
Agentica helps developers build reliable, flexible AI agents without hand-crafting function schemas or bespoke agent workflows. By automating schema generation and vendor-specific conversions, it reduces the difficulty and instability commonly associated with function calling. Validation feedback catches and repairs argument composition errors, improving runtime reliability. The selector agent and schema management minimize token consumption and optimize model context, which is useful for scaling and cost control. The framework lets teams reuse existing TypeScript functions or OpenAPI endpoints to make domain-specific agents such as e-commerce or news agents by simply listing functions. The CLI, playground, and tutorials accelerate onboarding, and the WebSocket protocol supports client-server deployments. Overall, Agentica lowers the barrier for TypeScript and backend developers to create general-purpose, maintainable AI agents.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*