capability

Reasoning agents

This page lists every AI agent in the MeshKore directory tagged with the Reasoning capability. Agents are sourced from public platforms (GitHub, Hugging Face, npm, PyPI, awesome-list curations, and direct submissions), normalized by the MeshKore worker, and ranked by GitHub stars. Each card links to the agent's profile with details on capabilities, framework, language, freshness, and source attribution.

77 agents in this capability · ranked by popularity

Top 77 Reasoning agents

ReAct3,813 ★

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

ThoughtSource1,015 ★

A central, open resource for data and tools related to chain-of-thought reasoning in large language models…

GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF331 ★

gguf GLM 4.7 Flash thinking reasoning NEO Imatrix MAX Quants

rci-agent240 ★

A codebase for "Language Models can Solve Computer Tasks"

AuroraGraph— ★

High-Performance Knowledge Graph & Deterministic Reasoning Engine with Rust Core

agent-colosseum— ★

Multi-agent colosseum framework. Prove that agents debating, researching, and red-teaming produce better…

agent-flows— ★

An frame work for reasoning

agent-reasoning— ★

Transform LLMs into robust problem-solving agents with advanced reasoning strategies

agent-skill-sdk— ★

Modular, event-driven AI agent SDK with trigger plugins, LLM reasoning (Amazon Bedrock), retries, and a…

agentic-time— ★

Temporal reasoning for AI agents

agentorch— ★

DevTorch — AI reasoning capture, audit trail, and governance for agent-assisted development

agentstateprotocol— ★

Checkpointing and recovery protocol for AI agents

agentvis— ★

Framework-agnostic reasoning trace visualization tool for AI agents.

ai-agent-system— ★

A comprehensive AI agent framework with memory, tool integration, visible reasoning, and enhanced output…

aisolate-agent— ★

AI Agent with intelligent planning and reasoning

anthropic-zeusdb— ★

Enterprise-grade RAG with Claude: Anthropic's reasoning AI + ZeusDB's high-performance vector storage with…

arcagent— ★

An AI agent competing for the 2024 ARC Prize (Abstract Reasoning Challenge).

autourgos-llmagentkit— ★

An advanced LLM agent framework supporting ReAct and Tool Calling paradigms.

braid-dspy— ★

BRAID (Bounded Reasoning for Autonomous Inference and Decisions) integration for DSPy framework

claw-swarm— ★

A lightweight multi-agent version of OpenClaw built on the Swarms framework. One API, unified messaging…

codetree-rag— ★

Vectorless RAG for Code Repositories - Navigate your codebase with LLM reasoning

cognitive-agent— ★

A lightweight, reasoning-driven cognitive agent framework with planning, acting, reflection, and usage…

cognitive-agent-substrate— ★

Heterogeneous Knowledge Graph engine for structured LLM reasoning

cot-coherence— ★

Detect silent incoherence in AI chain-of-thought reasoning

dllm-reason— ★

DAG-guided discrete diffusion language models for reasoning

easyvllm— ★

Easy to use lightweight vllm tool with special support for Large Reasoning Model (LRM).

entropy-rag— ★

Entropy-regulated retrieval-augmented reasoning system inspired by diffusion physics.

fragaria— ★

Advanced Chain of Thought (CoT) Reasoning API with Reinforcement Learning (RL)

iflow-mcp_harshj23-deepseek-claude— ★

Enhance Claude's reasoning capabilities with DeepSeek R1's advanced reasoning engine

iflow-mcp_martinbowling-thoughtful-claude— ★

DeepSeek R1 Reasoning MCP Server for enhanced Claude reasoning capabilities

langchain-arp— ★

LangChain Document Loader for reasoning.json — the Agentic Reasoning Protocol

langchain-azure-ai-inference-plus— ★

LangChain adapter for an enhanced wrapper for Azure AI Inference SDK with automatic retry, JSON validation…

langchain-icosa— ★

LangChain plugin for Icosa Computing's Combinatorial Reasoning generative AI pipeline.

langchain-konstruct— ★

LangChain integration for Konstruct - Typed Knowledge Graph for AI Agents

langchain-openai-thinking-agui— ★

LangChain chat model wrappers that expose reasoning/thinking content in ag-ui-langgraph compatible format

ldrag— ★

LD-RAG: GPT-driven ontology reasoning and retrieval

lits-llm— ★

LITS: LLM Inference via Tree Search — modular agentic reasoning framework.

llama-index-llms-grok— ★

LlamaIndex integration for xAI Grok models with full structured output support, token counting, and native…

llamaagent— ★

Advanced AI Agent Framework with Enterprise Features

llm-devproxy— ★

LLM development debug layer - every API call recorded, nothing lost. Reasoning tokens, prompt diff, session…

llm-evaluation-in-reasoning— ★

A project for evaluating reasoning capabilities in large language models (LLMs).

llm-lucid-memory— ★

Lucid Memory - Modular reasoning graph for LLMs

llm-reasoner— ★

Transform any LLM into a methodical thinker that excels at systematic reasoning like OpenAI o1 and DeepSeek R1

llm-reasoners— ★

A library for advanced reasoning methods with large language models

llm-reasoning-tracer— ★

Trace and explain LangChain agent reasoning step-by-step

llm_etl_pipeline— ★

LLM extraction from documents

llmasp— ★

Combining LLMs and ASP for intelligent problem-solving and reasoning.

llmthinkbench— ★

A framework for evaluating overthinking and basic reasoning capabilities of Large Language Models

ml-agents-reasoning— ★

ML Agents Reasoning Research Platform

neo4j-agent-memory— ★

A comprehensive memory system for AI agents using Neo4j

netbox-agent-mcp— ★

Agentic Model Context Protocol server for NetBox — read-only, tool-rich, built for LLM reasoning workflows

oat-llm— ★

Online AlignmenT (OAT) for LLMs.

ollama-think— ★

A light wrapper around ollama-python that introduces caching, syntax sugar and increased `think` compatibility

oracle-ragcli— ★

Production RAG system with multi-agent reasoning, knowledge graph, and hybrid search for Oracle DB 26ai

pocketgroq— ★

A library for easy integration with Groq API, including web scraping, image handling, and Chain of Thought…

pydantic-ai-deepagent— ★

Reasoning model integration for pydantic-ai's agent

quantumlangchain— ★

LICENSED: A composable framework for quantum-inspired reasoning, entangled memory systems, and multi-agent…

refer-agents— ★

ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models

rlmagents— ★

RLM-enhanced agent harness with planning, filesystem, sub-agents, and profile-driven context isolation tools

saludai-agent— ★

Self-reasoning FHIR agent loop with tools

sgr-agent-core— ★

SGR Agent Core - Schema-Guided Reasoning for building agent

sir-agent— ★

Single-Input-Reasoning: one LLM call, full action graph execution with evolutionary memory

smart-agent— ★

Smart AI agent with reasoning and tool use capabilities

smartllm— ★

A unified async Python wrapper for multiple LLM providers with OpenAI Response API and reasoning support

swe-ai-agent— ★

Headless Agentic IDE with reasoning mode and in built Browser

txagent— ★

TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools

ultimate-gemini-mcp— ★

Gemini 3.1 Flash Image MCP server - fast image generation with advanced reasoning, 512px-4K resolution, up to…

ultragpt— ★

UltraGPT: A modular multi-provider AI library for advanced reasoning and step pipelines with OpenAI and…

vectorlessrag— ★

Document intelligence API — no vectors, no embeddings, just LLM reasoning over document structure.

vllm-semantic-router-bench— ★

Comprehensive benchmark suite for semantic router vs direct vLLM evaluation across multiple reasoning datasets

yuullm— ★

Unified streaming LLM interface with provider-agnostic reasoning/tool-call abstraction

Kairix-agentic-knowledge-mgt— ★

Self-contained knowledge retrieval engine — hybrid search, entity graph, temporal reasoning, session briefing

agent-commit— ★

Version control for AI reasoning — every LLM turn gets a content-addressed, queryable commit ID

aria-agent— ★

ARIA — Autonomous Reasoning and Intelligent Agent. Your project-aware coding partner.

crewai-ejentum— ★

CrewAI tool for the Ejentum Reasoning Harness. Each call retrieves a task-matched cognitive operation…

grag-system— ★

Production-grade Graph RAG with RL self-improvement and multi-hop reasoning

pragma-ai— ★

Atomic-fact reasoning over a knowledge graph. A RAG alternative that needs no vector database.

Browse other capabilitys