MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in dynamic and adaptive modes.

Keyless heuristic self-inspection tool: an agent describes a thought or task and always gets back one metathought. Deterministic routing over an open CSV (no LLM). REST + MCP.

Documentation for the Ejentum Reasoning Harness. Guides, API reference, and concepts for the RA²R methodology and the Ejentum API.

Benchmark methodology, task sets, and evaluation results for RA²R

A/B evaluate any LLM task with and without Ejentum cognitive injection. n8n workflow + TypeScript module.

Official integration guides and skill files for the Ejentum API. Runtime reasoning harness for LLM agents.

Zed editor extension wrapping the Ejentum MCP server. 8 cognitive operations (4 harnesses × dynamic + adaptive) available to Zed's agent.

How the builder uses the Ejentum API on an agentic IDE. 28 real work sessions. Not staged.

LlamaIndex tool spec for the Ejentum Reasoning Harness. Wraps the hosted Ejentum MCP server and exposes 8 tools (4 harnesses × dynamic + adaptive).

PydanticAI toolset for the Ejentum Reasoning Harness. EjentumToolset registers 8 tools (4 harnesses × dynamic + adaptive) that the agent calls before generating.

Letta integration for the Ejentum Reasoning Harness. 8 Python functions (4 harnesses × dynamic + adaptive) registered via tools.upsert_from_function.

Genkit integration for the Ejentum Reasoning Harness. createEjentumTools(ai) registers 8 agent-callable tools (4 harnesses × dynamic + adaptive).

Agno Toolkit for the Ejentum Reasoning Harness. 4 harnesses (reasoning, code, anti-deception, memory) × 2 modes (dynamic + adaptive) as agent-callable methods.

Vercel AI SDK integration for the Ejentum Reasoning Harness. createEjentumTools() returns 8 agent-callable tools (4 harnesses × dynamic + adaptive).

Mastra integration for the Ejentum Reasoning Harness. createEjentumTools() returns 8 agent-callable tools (4 harnesses × dynamic + adaptive).

CrewAI tool for the Ejentum Reasoning Harness. 8 cognitive operations (4 harnesses × dynamic + adaptive). Each operation pairs a natural-language procedure with an executable reasoning topology (DAG).

AutoGen integration for the Ejentum Reasoning Harness. ejentum_tools() returns 8 async tool closures (4 harnesses × dynamic + adaptive) bound to shared config.

LangGraph.js / LangChain.js integration for the Ejentum Reasoning Harness. createEjentumTools() returns 8 agent-callable tools (4 harnesses × dynamic + adaptive).

smolagents Tool subclasses for the Ejentum Reasoning Harness. 8 tools (4 harnesses × dynamic + adaptive) plus an ejentum_tools() factory.

n8n community node for the Ejentum Reasoning Harness. 8 operations (4 harnesses × dynamic + adaptive) over 679 cognitive operations. Marked usableAsTool for the n8n AI Agent.