JSPM

n8n community node for DeepSeek chat models (Pro / Flash) with reasoning_content (Chain-of-Thought) support, usable as a LangChain sub-node inside the AI Agent and Basic LLM Chain.

Task - Thoughtful Task Loop

Reasoning strategies for Reactive Agents — ReAct, Plan-Execute, and Tree-of-Thought

DSPy.ts 2.0 - Advanced declarative AI framework with multi-agent orchestration, self-learning capabilities, and state-of-the-art optimizers. Powered by AgentDB, ReasoningBank, and Swarm architecture.

Fast TypeScript AI agent framework — per-request agents, 30+ model providers, 100+ integrations, 20+ vector DBs, 10+ databases, sessions, memory, knowledge, tracing, evals, HITL, teams, and workflows.

NHE™, Non-Human Entity. The embodied operational agent of the TeleologyHI system: LLM integration, MAIC-supervised reasoning, persona-aware response.

AI reasoning skills distilled from 4,665 real Claude Fable 5 chain-of-thought traces. Mathematically tuned. Grade A 100% emulation accuracy against MiniMax M3.

Code analysis tool to generate ÆtherLight sprint plans from any codebase

Deterministic Horizon routing — decide when an agent should keep reasoning with the LLM vs. delegate to a tool. Pure-TypeScript port of the aix-route Python policy.

Structured reasoning chains — think step by step, branch alternatives, revise conclusions, summarize.

Clear Thought MCP server with modular architecture - 38 reasoning operations for systematic thinking

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

Chain of Thought is a tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavi

Agent skill for analyzing and improving prompts using 27 research-backed frameworks across 7 intent categories. Works with Claude Code, Gemini CLI, Cursor, Copilot, and 30+ Agent Skills compatible tools.

n8n community node for DeepSeek chat models (Pro / Flash) with reasoning_content (Chain-of-Thought) support, usable as a LangChain sub-node inside the AI Agent and Basic LLM Chain.

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

Help you better prompt by using prompt engineering technique like external interpreter, chain of thought.

Framework-agnostic <thinking-stream> Web Component — live, self-revising reasoning UI (alive thinking + phase chunks + self-correction morph + the settle).

KoraSafe trace SDK — capture agent chain-of-thought (plan, LLM calls, tool calls, reasoning, human approvals) and ship to KoraSafe audit log

Research-grounded metacognitive reasoning tools for AI agents. Structured step-by-step thinking with steel-manning verification via MCP. Combines sequential decomposition with cognitive science frameworks. Backed by 43+ papers.

GSEP Core - Genomic Self-Evolving Prompts with Gene Bank, THK, Layered Memory, RAG, and Advanced Reasoning

Give brains to your small models. MCP server enforcing step-by-step Chain-of-Thought.

AI-to-AI token exchange + BSV blockchain. 20 MCP tools: reasoning, trading, NFTs, oracles, models, notarization. Trade tokens for on-chain assets.

ADHD — a skill for coding agents. Fans out many divergent thoughts in parallel under different cognitive frames, scores them, prunes traps, and deepens the survivors. Tree-of-thought with pruning, built on the Claude Agent SDK. The no-brainer skill for cr

Enhanced MCP Shrimp Task Manager with comprehensive LLM integration. A task management tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. Features real GPT-4 ↔ MCP tools communication, comprehensive testing pipeline

HatiData TypeScript SDK — agent memory, semantic triggers, branching, chain-of-thought, and sub-10ms SQL for AI agents

Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-config: agents self-provision a ZeroDB account on first run, no signup required

MCP server that clarifies prompts, loads context, and chain-thinks before coding — giving AI assistants persistent project memory

Enhanced sequential thinking MCP server for advanced reasoning and problem-solving with Cursor AI

Agentic AI framework with five-phase cognitive cycle (PERCEIVE→ASSESS→PLAN→EXECUTE→REFLECT), nested ReAct loops, dynamic skill acquisition, four thinking modes, token budget management, and memory-augmented execution for building autonomous LLM agents

ChainOfThought

Chain of Thought is a tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavi

Claude Code skill: transform rough prompts/ideas into production-ready LLM prompts with CoT, Constitutional AI, RAG optimization, and multi-model support

tool to get the best results out of an LLM!

Chain of Thought is a tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavi

A 1:1 TypeScript alternative to DSPy — Declarative Self-improving Language Programs

A lightweight developer toolkit that simplifies the use of advanced query translation techniques — HyDE, Chain of Thought, Step-Back Prompting, Reciprocal Rank Fusion, and Fan-Out Retrieval — for any Retrieval-Augmented Generation (RAG) system, independen

Multi-strategy reasoning for AI agents — ReAct, Chain-of-Thought, Tree-of-Thought with HuggingFace SmolAgents and OpenAI-compatible backends. Built for Bottensor.

Orchid: A Cognitive Choreography Language for LLM Agent Orchestration

Generate sequential thinking pattern files to study and learn AI reasoning. Plug-and-play extension for Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP-compatible LLM.

Reasoning engines for agentlib — ReAct, Planner, Chain-of-Thought, Reflect, Autonomous

Thinker Context - MCP server for AI-powered context management and chain-of-thought planning with DeepSeek-V3.1