ReasonKit

The Reasoning Engine

"From Prompt to Cognitive Engineering." -- Turn Prompts into Protocols.

Auditable Reasoning for Production AI | Rust-Native | SSR/SSG Compatible

Website | Documentation | GitHub

The Problem We Solve

Most AI is a slot machine. Insert prompt -> pull lever -> hope for coherence.

ReasonKit is a factory. Input data -> execute protocol -> get deterministic, auditable output.

LLMs are fundamentally probabilistic. Same prompt -> different outputs. This creates critical failures:

We don't eliminate probability (impossible). We constrain it through structured protocols that force probabilistic outputs into deterministic execution paths.

Quick Start

# Install (Universal)
curl -fsSL https://reasonkit.sh/install | bash

# Or via Cargo
cargo install reasonkit-core

# Run your first analysis
rk-core think --profile balanced "Should we migrate to microservices?"

Note: Some CLI commands are scaffolded in v0.1.0. Core functionality (mcp, serve-mcp, completions) is fully implemented.

30 seconds to structured reasoning.

ThinkTools: The 5-Step Reasoning Chain

Each ThinkTool acts as a variance reduction filter, transforming probabilistic outputs into increasingly deterministic reasoning paths.

The PowerCombo Process: Five cognitive operations that systematically reduce variance from raw LLM output (~85%) to protocol-constrained reasoning (~28%)

Variance Reduction: The Chain Effect

Quantified Uncertainty Reduction: Each ThinkTool stage measurably constrains probabilistic variance

Result: Raw LLM variance ~85% -> Protocol-constrained variance ~28%

Reasoning Profiles

Pre-configured chains for different rigor levels:

# Fast analysis (70% confidence target)
rk-core think --profile quick "Is this email phishing?"

# Standard analysis (80% confidence target)
rk-core think --profile balanced "Should we use microservices?"

# Thorough analysis (85% confidence target)
rk-core think --profile deep "Design A/B test for feature X"

# Maximum rigor (95% confidence target)
rk-core think --profile paranoid "Validate cryptographic implementation"

See It In Action

Live Execution Trace: Every reasoning step logged with confidence scores and variance metrics

$ rk-core think --profile balanced "Should we migrate to microservices?"

ThinkTool Chain: GigaThink -> LaserLogic -> BedRock -> ProofGuard
Variance:        85% -> 72% -> 58% -> 42% -> 28%

[GigaThink] 10 PERSPECTIVES GENERATED                         Variance: 85%
  1. OPERATIONAL: Maintenance overhead +40% initially
  2. TEAM TOPOLOGY: Conway's Law - do we have the teams?
  3. COST ANALYSIS: Infrastructure scales non-linearly
  ...
  -> Variance after exploration: 72% (-13%)

[LaserLogic] HIDDEN ASSUMPTIONS DETECTED                      Variance: 72%
  ! Assuming network latency is negligible
  ! Assuming team has distributed tracing expertise
  ! Logical gap: No evidence microservices solve stated problem
  -> Variance after validation: 58% (-14%)

[BedRock] FIRST PRINCIPLES DECOMPOSITION                      Variance: 58%
  * Axiom: Monoliths are simpler to reason about (empirical)
  * Axiom: Distributed systems introduce partitions (CAP theorem)
  * Gap: Cannot prove maintainability improvement without data
  -> Variance after grounding: 42% (-16%)

[ProofGuard] TRIANGULATION RESULT                             Variance: 42%
  * 3/5 sources: Microservices increase complexity initially
  * 2/5 sources: Some teams report success
  * Confidence: 0.72 (MEDIUM) - Mixed evidence
  -> Variance after verification: 28% (-14%)

VERDICT: conditional_yes | Confidence: 87% | Duration: 2.3s

What This Shows:

• Transparency: See exactly where confidence comes from
• Auditability: Every step logged and verifiable
• Deterministic Path: Same protocol -> same execution flow
• Variance Reduction: Quantified uncertainty reduction at each stage

Architecture

Three-Layer Architecture: Deterministic protocol engine wrapping probabilistic LLM layer with full execution tracing

Three-Layer Architecture:

1. Probabilistic LLM (Unavoidable)

   • LLMs generate tokens probabilistically
   • Same prompt -> different outputs
   • We cannot eliminate this

2. Deterministic Protocol Engine (Our Innovation)

   • Wraps the probabilistic LLM layer
   • Enforces strict execution paths
   • Validates outputs against schemas
   • State machine ensures consistent flow

3. ThinkTool Chain (Variance Reduction)

   • Each ThinkTool reduces variance
   • Multi-stage validation catches errors
   • Confidence scoring quantifies uncertainty

Key Components:

• Protocol Engine: Orchestrates execution with strict state management
• ThinkTools: Modular cognitive operations with defined contracts
• LLM Integration: Unified client (Claude, GPT, Gemini, 18+ providers)
• Telemetry: Local SQLite for execution traces + variance metrics

flowchart LR
    subgraph CLI["ReasonKit CLI (rk-core)"]
      A[User Command<br/>rk-core think --profile balanced]
    end

    subgraph PROTOCOL["Deterministic Protocol Engine"]
      B1[State Machine<br/>Execution Plan]
      B2[ThinkTool Orchestrator]
      B3[(SQLite Trace DB)]
    end

    subgraph LLM["LLM Layer (Probabilistic)"]
      C1[Provider Router]
      C2[Claude / GPT / Gemini / ...]
    end

    subgraph TOOLS["ThinkTools - Variance Reduction"]
      G["GigaThink<br/>Diverge()"]
      LZ["LaserLogic<br/>Converge()"]
      BR["BedRock<br/>Ground()"]
      PG["ProofGuard<br/>Verify()"]
      BH["BrutalHonesty<br/>Critique()"]
    end

    A --> B1 --> B2 --> G --> LZ --> BR --> PG --> BH --> B3
    B2 --> C1 --> C2 --> B2

    classDef core fill:#030508,stroke:#06b6d4,stroke-width:1px,color:#f9fafb;
    classDef tool fill:#0a0d14,stroke:#10b981,stroke-width:1px,color:#f9fafb;
    classDef llm fill:#111827,stroke:#a855f7,stroke-width:1px,color:#f9fafb;

    class CLI,PROTOCOL core;
    class G,LZ,BR,PG,BH tool;
    class LLM,llm C1,C2;

Built for Production

ReasonKit is written in Rust because reasoning infrastructure demands reliability.

Benchmarked Performance (view full report):

Why This Matters:

Your AI reasoning shouldn't crash in production. It shouldn't pause for garbage collection during critical decisions. It shouldn't require complex environment management to deploy.

ReasonKit's Rust foundation ensures deterministic, auditable execution every time--the same engineering choice trusted by Linux, Cloudflare, Discord, and AWS for their most critical infrastructure.

Memory Infrastructure (Optional)

Memory modules (storage, embedding, retrieval, RAPTOR, indexing) are available in the standalone reasonkit-mem crate.

Enable the memory feature to use these modules:

[dependencies]
reasonkit-core = { version = "0.1", features = ["memory"] }

Features:

• Qdrant vector database (embedded mode)
• Hybrid search (dense + sparse fusion)
• RAPTOR hierarchical retrieval
• Local embeddings (BGE-M3 ONNX)
• BM25 full-text search (Tantivy)

Installation

Primary Method (Universal):

curl -fsSL https://reasonkit.sh/install | bash

# Cargo (Rust) - Recommended for Developers
cargo install reasonkit-core

# npm (Node.js) - CLI Wrapper
npm install -g @reasonkit/cli

# uv (Python) - Bindings Only
uv pip install reasonkit

Usage Examples

Standard Operations:

# Balanced analysis (5-step protocol)
rk-core think --profile balanced "Should we migrate our monolith to microservices?"

# Quick sanity check (2-step protocol)
rk-core think --profile quick "Is this email a phishing attempt?"

# Maximum rigor (paranoid mode)
rk-core think --profile paranoid "Validate this cryptographic implementation"

# Scientific method (research & experiments)
rk-core think --profile scientific "Design A/B test for feature X"

With Memory (RAG):

# Ingest documents
rk-core ingest document.pdf

# Query with RAG
rk-core query "What are the key findings in the research papers?"

# View execution traces
rk-core trace list
rk-core trace export <id>

Contributing: The 5 Gates of Quality

We demand excellence. All contributions must pass The 5 Gates of Quality:

# Clone & Setup
git clone https://github.com/reasonkit/reasonkit-core
cd reasonkit-core

# The 5 Gates (MANDATORY)
cargo build --release        # Gate 1: Compilation (Exit 0)
cargo clippy -- -D warnings  # Gate 2: Linting (0 errors)
cargo fmt --check            # Gate 3: Formatting (Pass)
cargo test --all-features    # Gate 4: Testing (100% pass)
cargo bench                  # Gate 5: Performance (<5% regression)

Quality Score Target: 8.0/10 minimum for release.

See CONTRIBUTING.md for complete guidelines.

Design Philosophy: Honest Engineering

We don't claim to eliminate probability. That's impossible. LLMs are probabilistic by design.

We do claim to constrain it. Through structured protocols, multi-stage validation, and deterministic execution paths, we transform probabilistic token generation into auditable reasoning chains.

License

Apache 2.0 - See LICENSE

Open Source Core: All core reasoning protocols and ThinkTools are open source under Apache 2.0.

Website | Documentation | GitHub