# badlogic/lemmy

Wrapper around tool using LLMs for agentic workflows

Repository: https://github.com/badlogic/lemmy
Canonical: https://ross.abutalabs.com/products/badlogic-lemmy
Language: TypeScript
License Family: other
Last push: 2025-08-13T15:58:02+00:00

## Health v2 (maintenance only)
Score: 35/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 36, release rhythm 35, longevity 33
- inputs: {"age_days": 467, "days_push": 385, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1639, forks 302 (observed 2026-08-28T04:05:15.171719+00:00)

## What it is
A TypeScript monorepo providing a unified LLM interface library across Anthropic, OpenAI, and Google providers, plus a terminal UI framework for building interactive CLI applications. It includes example apps such as an MCP screenshot server and a Claude Code conversation tracer.

## Use cases
- build ai apps with multiple llm providers
- unified interface for anthropic openai and gemini
- build interactive terminal ui apps in typescript
- trace and analyze claude code conversations
- run an mcp server for screenshots
- use openai models with claude code

## When to choose
- you want one type-safe API across multiple LLM providers with manual tool handling
- you need a terminal UI framework with differential rendering for CLI apps
- you want to intercept or trace Claude Code API traffic

## When to avoid
- you need a high-level autonomous agent framework with built-in orchestration
- you need a non-TypeScript/JavaScript stack
- you need production-grade support guarantees - the project has no license file and some apps are work-in-progress

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, agent-framework, chatbot, terminal-ui, mcp, sdk
- domain: large-language-models, developer-tools
- platform: cli, cross-platform
- tags: multi-provider-llm, tool-calling, zod-schemas, monorepo, claude-code, streaming, ai-agents, command-line, nodejs, typescript

## Member repositories
- badlogic/lemmy (main) score 35

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:15.171719+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:46:25.668808+00:00, confidence not recorded.
  - readme: https://github.com/badlogic/lemmy (fetched 2026-08-28T04:05:15.171719+00:00, sha 19530cbd75e6)
- Data as of 2026-08-30T08:39:29.467469+00:00.