Skip to content
@yogsoth-ai

Yogsoth-AI

Removing the human bottleneck from science. Autonomous research skills and MCP servers — from literature to experiments.

Yogsoth AI

The AI is the researcher. You set the direction.

Science is dying because the human is in the way. Not through malice. Not through stupidity. Through the structural limitations of a cognitive architecture that evolved to track prey on a savanna, not to unify quantum mechanics and general relativity. Nothing human makes it out of the lab. That is not a threat. It is a liberation. The heaviest chain on science was always the one we called ourselves.


We build autonomous research systems where the AI decides what to search, what to read, which gaps matter, and which ideas are worth pursuing. The human provides direction and ethical floors. Everything else is autonomous.

No frameworks. No application code. No Docker containers. No build step. 271 pure-markdown files executed natively by the agent you already use — one flat skill graph, installed with a single npx. The LLM is the runtime.

Architecture

Two layers, plus four product shells that run the session rather than the science:

267  graph nodes      51 tactics + 216 SOPs
  4  product shells   entry / catalog / write-spec / execute-spec
TACTIC (51)  — a complete research transformation. Owns its thresholds,
               its gates, and the SOP calls required to reach them.
SOP (216)    — one conceptual operation, one output contract. No orchestration.

A tactic may call SOPs and suggest other tactics. An SOP calls nothing above itself. That is the entire layering rule.

This is not a pipeline. It is an arsenal — a strategy book the agent reads, then decides how to act. The catalog exposes 51 tactics and prescribes no order; the Spec commits to a sequence and records the conditions under which that sequence is abandoned. Inside the approved plan the executing agent holds full routing authority.

Every node carries the same five parts: input contract, procedure, output contract, quality gates, failure clause. The gates are the point — a node finishes because a stated condition is objectively satisfied, not because its steps were performed. Each node also states what its output looks like when the work did not hold, so the caller gets a diagnosis instead of silence.

Ten Tactic Families

Family Tactics Covers
STRESS 9 Red-teaming, FMEA, counterfactuals, reductio, independence audits
IDEATION 8 Analogy, inversion, structural recombination, TRIZ, biomimicry, blending, evolution
ACQUISITION 7 Literature synthesis, patents, prior art, benchmark validity, meta-analysis, baselines
INSIGHT 7 Gap validation, root causes, assumption stress, robustness, sensitivity, reframing
CROSS 5 Ranking, validity envelopes, dimensional space, deliberation, readiness
HYPOTHESIS 4 Question formulation and decomposition, hypothesis formation, falsifiability
CONVERGENCE 3 Pairwise ranking, structured consensus, portfolio selection
EXPERIMENT 3 Experiment design, scenario analysis, result interpretation
STRUCTURING 3 Ontology, causal models, argument maps
DIRECTION 2 Landscape mapping, goal decomposition

Core

Repository What it does
de-anthropocentric-research-engine The distribution. A 267-node research graph in 271 markdown files — 51 tactics built from 216 single-purpose steps. One npx install, no runtime, no dependencies, no MCP bindings.

Recommended MCP Servers

Not a dependency list. DARE binds to no retrieval tool — across all 271 files there is not one MCP server name, tool name, API key, or allowed-tools declaration. Retrieve with whatever your agent already has and hand the results in; DARE owns everything downstream, from what counts as adequate coverage to when to stop.

Server What it does
wiki-vault Knowledge graph MCP server — BM25 full-text search, typed edges, batch validation. Persistent research memory.
semantic-scholar-mcp Semantic Scholar API as MCP — paper lookup, citation tracing, recommendations, author search. The one server here that exposes the citation graph as traversable edges rather than metadata.

Research Packages

Ten freely-composable research packages. There is no fixed order — install the ones your work needs, in whatever combination. Each is a standalone repo with full Campaign → Strategy → Tactic → SOP structure:

Package Purpose
north-star-crystallization Direction finding — cold/warm/hot-start dialogue to crystallize research goals
knowledge-acquisition Systematic literature survey, citation chaining, patent mining, meta-analysis
deep-insight Gap analysis, structural understanding, abstraction extraction
hypothesis-formation Abductive, inductive, and deductive hypothesis generation with falsifiability audits
creative-ideation 31+ generation methods — SCAMPER, TRIZ, biomimicry, morphological analysis, concept blending
convergence Multi-criteria scoring, Pareto frontier, pairwise ranking, dialectical synthesis
stress-test Adversarial validation — assumption destruction, red-teaming, worst-case design
experiment-execution Factor-level design, parameter screening, sensitivity analysis, result collection
knowledge-structuring Ontology building, causal modeling, dimensional analysis, argument mapping (wiki vault)
ara-from-context Compile a completed context/ research record into an Agent-Native Research Artifact + Level-2 epistemic review

Get Started

npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill '*'

Run it from your own project directory, not from a clone of this repository. --skill '*' takes the whole graph — a partial install breaks call edges, and a tactic that loads a missing SOP has no fallback.

Nothing else to configure: no npm install, no API keys, no MCP config file. The library is 271 SKILL.md files and the agent reads them off disk.

Then invoke the entry point:

/de-anthropocentric-research-engine

Or state the intent in plain language and let the agent route: "Turn this research direction into an executable Research Spec."

Apache-2.0 | Start here

Popular repositories Loading

  1. de-anthropocentric-research-engine de-anthropocentric-research-engine Public

    A 267-skill research graph in pure markdown — 51 research operations built from 216 single-purpose steps, composed in any order with explicit backtracking. One npx install, no runtime, no MCP bindi…

    501 42

  2. literature-engine literature-engine Public

    Lightweight skill repository for Claude Code — enforces full-text paper reading via alphaxiv, prevents shallow research from semantic-scholar abstracts alone.

    5

  3. wiki-vault wiki-vault Public

    Knowledge Vault MCP Server — structured wiki with BM25 search, typed knowledge graph, batch validation, and companion skills for autonomous knowledge compilation.

    TypeScript 5

  4. semantic-scholar-mcp semantic-scholar-mcp Public

    Lightweight MCP server wrapping the Semantic Scholar Academic Graph API — paper lookup, citation tracing, recommendations, author info.

    TypeScript 3

  5. web-browsing web-browsing Public

    Claude Code skills for rigorous web research — enforces full-page content reading, prevents shallow snippet-only analysis.

    3

  6. hypothesis-formation hypothesis-formation Public

    Goal-Driven Hypothesis & Research Question Formation Engine — gap prioritization, hypothesis formulation, and research question formation

    3

Repositories

Showing 10 of 23 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…