Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 21 of 26

openbmb.AgentCPM-Explore-GGUF★ 1

gguf text-generation base_model:openbmb/AgentCPM-Explore base_model:quantized:openbmb/AgentCPM-Explore endpoints_compatible region:us

gemma-4-26B-A4B-it-assistant-NVFP4★ 1

transformers safetensors gemma4_assistant text-generation gemma gemma4

Weni-ZeroShot-Agents-Llama3-4.0.11-SFT-merged-GGUF★ 1

gguf text-generation base_model:Weni/ZeroShot-Agents-Llama3-4.0.11-SFT-merged base_model:quantized:Weni/ZeroShot-Agents-Llama3-4.0.11-SFT-merged endpoints_compa

nesso2-0.4B-agentic★ 1

transformers safetensors llama text-generation small-language-model slm

ByteDance-Seed.M3-Agent-Control-GGUF★ 1

gguf text-generation base_model:ByteDance-Seed/M3-Agent-Control base_model:quantized:ByteDance-Seed/M3-Agent-Control endpoints_compatible region:us

Anubis-559M★ 1

transformers safetensors anubis_moe text-generation anubis custom_code

qwen0.5b-tinylora-ds-assistant★ 1

transformers safetensors layer_grow text-generation sft layer-grow

Atlas-Chat-2B-GGUF★ 1

transformers gguf conversational text-generation ar dataset:MBZUAI-Paris/Darija-SFT-Mixture

Mistral-NeMo-Minitron-8B-Chat-GGUF★ 1

transformers gguf text-generation dataset:teknium/OpenHermes-2.5 base_model:nvidia/Mistral-NeMo-Minitron-8B-Base base_model:quantized:nvidia/Mistral-NeMo-Minitr

LlamaCorn-1.1B-Chat-GGUF★ 1

gguf alignment-handbook generated_from_trainer trl sft text-generation

IntervitensInc-Mistral-Nemo-Base-2407-chatml-GGUF★ 1

gguf text-generation base_model:IntervitensInc/Mistral-Nemo-Base-2407-chatml base_model:quantized:IntervitensInc/Mistral-Nemo-Base-2407-chatml endpoints_compati

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-moist_regal_mule★ 1

transformers safetensors qwen2 text-generation rl-swarm genrl-swarm

small-agentic-model-1.5B★ 1

transformers tensorboard safetensors gpt2 text-generation generated_from_trainer

voho-saudi-chat-4b★ 1

transformers safetensors qwen3 text-generation arabic saudi-arabic

robby-chat-model★ 1

transformers safetensors qwen2 text-generation unsloth qwen2.5

LFM2.5-230M-Propella★ 1

safetensors lfm2 text-generation conversational en dataset:agentlans/c4-en-propella

gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF★ 1

gguf gemma4 coding agentic terminal tool-use

gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF★ 1

gguf gemma4 coding agentic terminal tool-use

Agentic-30B-A3B★ 1

transformers safetensors qwen3_moe text-generation agent agentic

SuperQwen-AgentWorld-35B-A3B-abliterated-Q5_0-GGUF★ 1

transformers gguf qwen qwen-agentworld world-model agent

slm-research-vn.EdgeRunner-Command-AgentF-qwen-GGUF★ 1

gguf text-generation base_model:slm-research-vn/EdgeRunner-Command-AgentF-qwen base_model:quantized:slm-research-vn/EdgeRunner-Command-AgentF-qwen endpoints_com

gemma-4-31B-it-assistant-MTP-GGUF★ 1

gguf mtp draft-model assistant speculative-decoding gemma4

JSBAI-Coder-4B★ 1

transformers safetensors qwen3_5_text text-generation agentic-coding reasoning

Qwen3-Coder-30B-A3B-Instruct-AWQ★ 1

transformers safetensors qwen3_moe text-generation conversational arxiv:2505.09388

MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF★ 1

transformers gguf minicpm minicpm5 llama text-generation

azma-open-hermes-2.5-agent-v1★ 1

transformers safetensors mistral text-generation conversational arxiv:1910.09700

MasryGPT-Chat-1.5B★ 1

transformers safetensors qwen2 text-generation qwen2.5 arabic

evo-ai★ 1

Distributed self-evolving language model network. 813K-param model evolving via (1+lambda)-ES across volunteer nodes. Public API + A2A JSON-RPC 2.0.

Qwen3.8-27B-OBLITERATED22-AGENT★ 1

mlx safetensors gguf qwen3_5 abliterated uncensored

lfm2.5-2.6b-fable5-coding-agent-heretic★ 1

safetensors gguf lfm2 heretic uncensored decensored

nesso3-0.4B-agentic★ 1

transformers safetensors llama text-generation small-language-model slm

llama-3.2-1b-mini-agent★ 1

peft safetensors gguf llama llama-3.2 lora

colgrep-agent-2B-ONNX★ 1

onnx llama onnxruntime quantized text-generation base_model:lightonai/colgrep-agent-2B

s1-gemma4-26b-decision★ 1

transformers safetensors gemma4 image-text-to-text decision-making classification

ari-assistant-3b★ 1

safetensors gguf qwen2 conversational code ari-llm

mgi-assistant-v1-qwen3-4b★ 1

transformers safetensors qwen3 text-generation unsloth lora

hpc-assistant-qwen3-4b★ 1

transformers safetensors gguf qwen3 text-generation hpc

Udgam-384M-Chat-MLX★ 1

mlx safetensors gemma4_text udgamlabs gemma4 tool-calling

Nanbeige-16B-Chat-GGUF★ 1

transformers gguf nanbeige llm Nanbeige custom_code

mistral-2.7b-tinystories-ba700★ 1

transformers pytorch mistral text-generation text-generation-inference endpoints_compatible

jais-6p7b-chat★ 1

transformers pytorch gpt2 text-generation text-generation-inference endpoints_compatible

CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m★ 1

transformers gguf llama text-generation-inference unsloth q4_k_m

deepseek-llm-7b-chat-abliterated★ 1

transformers safetensors llama text-generation abliteration uncensored

Qwen1.5-0.4B-Chat★ 1

transformers safetensors qwen2 text-generation conversational arxiv:1910.09700

Tessera-1B-Nano★ 1

transformers safetensors ncp_smol text-generation next-concept-prediction conceptlm

Tessera-1B-Nano-Base★ 1

transformers safetensors llama text-generation next-concept-prediction conceptlm

functiongemma-270m-it-simple-tool-calling★ 1

transformers tensorboard safetensors gemma3_text text-generation generated_from_trainer

huihui-ai-Qwen2.5-Coder-7B-Instruct-abliterated-GGUF★ 1

gguf text-generation base_model:huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated base_model:quantized:huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated endpoints_c

gemma-4-E2B-it-agent-posttrain-v1.2★ 1

transformers safetensors gguf gemma tool-calling function-calling

gemma-4-E2B-it-agent-posttrain-v1.3★ 1

transformers safetensors gguf gemma tool-calling function-calling

Llama-PLLuM-70B-chat-GGUF★ 1

gguf text-generation base_model:CYFRAGOVPL/Llama-PLLuM-70B-chat-2412 base_model:quantized:CYFRAGOVPL/Llama-PLLuM-70B-chat-2412 license:llama3.1 endpoints_compat

Qwen3-Coder-Next-GGUF★ 1

transformers gguf text-generation license:apache-2.0 endpoints_compatible region:us

Qwen2.5-Coder-1.5B-Instruct-Q4_K_M-GGUF★ 1

transformers gguf code codeqwen chat qwen

diffusiongemma-agent-iq3-cuda13★ 1

diffusiongemma-agent gguf diffusiongemma coding-agent cuda wsl

hasib-ai-chatbot★ 1

transformers safetensors gpt2 text-generation arxiv:1910.09700 text-generation-inference

codium-bd-coder-v2-lora★ 1

safetensors gguf qwen2 lora code programming

Arabian-Agent-Qwen3-0.6B★ 1

transformers safetensors qwen3 text-generation arabic tool-use

hpc-assistant-qwen3-8b★ 1

transformers safetensors gguf qwen3 text-generation hpc

hpc-assistant-fix4-gguf★ 1

transformers safetensors gguf qwen3 text-generation hpc

Qwen2.5-Coder-14B-Instruct-3MPER0RR-abliterated★ 1

safetensors qwen2 conversational text-generation-inference text-generation base_model:Qwen/Qwen2.5-Coder-14B-Instruct

Kimi-Linear-48B-A3B-Code-CMF★ 1

cortiq cmf kimi-linear kda moe quantized

QwenPaw-Flash-27B-BF16★ 1

gguf qwenpaw tool-use text-generation license:apache-2.0 endpoints_compatible

ThoxNova-12B-Agent★ 1

peft safetensors gguf thox lora sft

QwenDGAF-Coder-0.5B★ 1

gguf qwen2 qwen2.5-coder code coding-assistant slacker

QwenDGAF-Coder-1.5B★ 1

gguf qwen2 qwen2.5-coder code coding-assistant slacker

deepseek-r1

DeepSeek R1 review: compare features, pricing, use cases, access model, and alternatives for this LLM agent in 2026. An open-source reasoning in LLM from DeepSeek!

mistral-small-3

Mistral Small 3 review: compare features, pricing, use cases, access model, and alternatives for this LLM agent in 2026. Efficient, open-source AI model rivaling larger competitors with lower resource requirements.

deepcoder-14b-preview

DeepCoder-14B-Preview review: compare features, pricing, use cases, access model, and alternatives for this Code Generation agent in 2026. Revolutionizing AI-Powered Code Generation from DeepSeek-R1-Distilled-Qwen-14B

openpipe

OpenPipe TypeScript SDK: Fine-Tuning, Inference, and Metrics for Production Apps

@sap-ai-sdk/rpt

This package provides a client for SAP’s Relational Pretrained Transformer model, SAP-RPT-1.

@aws-sdk/client-sagemaker-a2i-runtime

AWS SDK for JavaScript Sagemaker A2i Runtime Client for Node.js, Browser and React Native

agent-lightning-sdk

TypeScript SDK for Agent Lightning - Train and optimize AI agents with Reinforcement Learning

tuningengines-cli

Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p

Agent-Smith

Python Reinforcement Learning Library with PyTorch

AgentJet
AgenticLearnPro

A simple agentic AI package using reinforcement learning

Andromeda-llm

andromeda - Pytorch

BiLLM

Tool for converting LLMs from uni-directional to bi-directional for tasks like classification and sentence embeddings.

Donut-LLM-Tools

Tools for creating datasets, training and loading AI models

DonutLLMCore

Core library for training PyTorch model in Donut-LLM-Tools

FineTune-Mistral

A package for fine-tuning Mistral model and generating responses.

FineTune-Uunsloth-Mistral-7b

A package for fine-tuning Mistral model and generating responses.

GPT2LM

Implementation of GPT-2 language model for text generation, training custom models and fine-tuning.

HydraGNN

Distributed PyTorch implementation of multi-headed graph convolutional neural networks

LLM4TS

LLM4TS

NeodroidAgent

Reinforcement learning agent implementations, intended for use with the Neodroid platform

PyMiniGPT

A small GPT model

QAgentLib

A reinforcement learning library inspired by Agentic Learn Pro, focusing on Q-learning.

Quant-AgentTools

Agentic Workflow with Quantized LLMs

SimpleQAgents

Simple deep q agents for gymnasium environments

SwarmML

Feature Selection with PSO

SwarmPackagePy

Library of swarm optimization algorithms.

Text-Classifier-based-Openai-Community-gpt2

A library that leverages the pre-trained openai-community/gpt2 model for multilingual text classification (French, German, and English), providing straightforward fine-tuning capabilities for sequence classification tasks.

adamix-gpt2

PyTorch implementation of low-rank adaptation (LoRA) and Adamix, a parameter-efficient approach to adapt a large pre-trained deep learning model which obtains performance better than full fine-tuning.

adaswarm

A PyTorch particle-swarm-optimisation loss function that augments gradient-based optimisers with swarm intelligence.

agent-attention-pytorch

Agent Attention - Pytorch

agent-gpt-aws

AgentGPT CLI for training and inference on AWS SageMaker

agent-rollouts

A CLI to get training data from your own coding agents. Track rollouts and codebase snapshots at every turn. The data can be used for SFT, RL, and Continual Learning.

agent-torch

large population models

agentcore-rl-toolkit

Toolkit for Seamlessly Enabling RL Training with Bedrock AgentCore.

More in Agent frameworks & infrastructure