| Name | Version | Summary | date |
| kalavai-client |
0.6.18 |
Client app for kalavai platform |
2025-07-19 11:17:08 |
| model-forge-llm |
0.2.1 |
A reusable library for managing LLM providers, authentication, and model selection. |
2025-07-19 09:50:42 |
| dacp |
0.3.4 |
Declarative Agent Communication Protocol - A protocol for managing LLM/agent communications and tool function calls |
2025-07-19 08:47:26 |
| imagesorcery-mcp |
0.4.1 |
A Model Context Protocol server providing image manipulation tools for LLMs |
2025-07-19 06:47:54 |
| evalassist |
0.1.17 |
EvalAssist is an open-source project that simplifies using large language models as evaluators (LLM-as-a-Judge) of the output of other large language models by supporting users in iteratively refining evaluation criteria in a web-based user experience. |
2025-07-18 19:41:56 |
| ai-dynamo-runtime |
0.3.2 |
Dynamo Inference Framework Runtime |
2025-07-18 14:21:47 |
| ai-microcore |
4.2.5 |
# Minimalistic Foundation for AI Applications |
2025-07-18 09:25:50 |
| chainlit-aki |
2.6.2 |
Build Conversational AI. (Custom fork of Chainlit for Aki) |
2025-07-18 02:23:07 |
| mcp-cli |
0.5.1 |
A cli for the Model Context Provider |
2025-07-17 21:37:39 |
| portia-sdk-python |
0.5.0 |
Portia Labs Python SDK for building agentic workflows. |
2025-07-17 14:44:01 |
| RAGnificentAI |
1.2 |
A simple RAG chatbot supporting multiple LLM providers |
2025-07-17 13:36:54 |
| RAGnificent |
1.0 |
A simple RAG chatbot supporting multiple LLM providers |
2025-07-17 10:48:10 |
| chainlit-hl-custom |
2.6.2 |
Build Conversational AI. (Custom fork of Chainlit) |
2025-07-17 08:46:24 |
| lm-council |
0.1.0 |
A framework for LLM evaluation through multi-judge councils |
2025-07-17 06:53:05 |
| galileo-core |
3.58.0 |
Shared schemas and configuration for Galileo's Python packages. |
2025-07-16 23:19:00 |
| llm-chutes |
0.1.0 |
LLM plugin for models hosted by Chutes AI |
2025-07-16 20:36:41 |
| llm-batch-helper |
0.1.2 |
A Python package that enables batch submission of prompts to LLM APIs, with built-in async capabilities and response caching. |
2025-07-16 17:35:51 |
| judgezoo |
0.1.1 |
A collection of judges for evaluating LLM model output for safety & toxicity with a standardized API. |
2025-07-16 13:49:03 |
| rwkv-tokenizer |
0.11.0 |
RWKV Tokenizer |
2025-07-16 09:53:48 |
| openaivec |
0.9.7 |
Generative mutation for tabular calculation |
2025-07-16 05:00:53 |