Pre-Release

The cognition layer
for AI agents.

One gateway. Seven planes. Up to 91% fewer tokens.

agent.ctx

Why standard tools fail agents.

Agents process language natively. Forcing them to communicate via dense infra JSON breaks their context window and cripples autonomy.

Context Waste

Agents waste 55-105K tokens per session navigating tool schemas and repetitive JSON structures.

High Latency Maxed Budgets

No Memory

Every session starts completely empty. Zero persistence of yesterday's architecture decisions or working context.

Redundant Work Context Dropped

No Trust Layer

Invisible boundaries. No cryptographic proof connecting what the agent actually did to what the human reviewer was told.

Security Blindspot No Audit Trail

Up to 91% Compression on the Wire

Interactive before/after: See the token difference between standard JSON-RPC and AgentCTX.

payload.jsonStandard MCP
5.7×
Token Compression
average across 12 operation types
4.8M
Parser Throughput
ops/sec — never a bottleneck
0.78ms
Memory Lookup
flat to 50,000 entries
765K
Sidecar Speed
translations/sec (trust at wire speed)

Bigger Context Windows Are Compounding Debt

CTX is Compounding Value.

Without CTX

16K
32K
64K
128K
200K

More window → more overhead → more cost → diminishing returns

VS

With CTX

16K
32K
64K
128K
200K

Same window → less overhead → more reasoning space → compounding returns

75.5% of GPT-4o's context is consumed by overhead before reasoning begins
5.7× compression ratio with CTX-Native mode, measured across 9 benchmarks
91% token reduction on static content via Content-Addressable Store (CAS)

Restore the Context Window

Tokens spent on infra syntax are tokens stolen from agent reasoning.

Theory of Computation

The Operating System for AI

POSIX gave processes a common interface to hardware. CTX gives agents a common interface to cognition. It is a complete synthesis.

01

The ISA (Grammar)

Instead of x86 instructions, AgentCTX defines a deterministic operational grammar (CTX). Models emit raw syntax strings that are guaranteed to compile, eliminating JSON-RPC hallucinations and validation loops.

02

The Kernel (Gateway)

The centralized routing engine. It parses CTX streams, enforces zero-trust memory segmentation, and orchestrates agent-to-agent Inter-Process Communication (IPC) via internal memory graphs.

03

The Process (Agent)

LLM Agents operate as isolated runtimes. They can spawn child processes (sub-agents) and pass file descriptors (memory pointers), while the Kernel handles state management and fault tolerance.

04

Memory Paging (CTX/CAS)

The system never transmits redundant context. Using Content-Addressable Storage (CAS) and the CTX grammar, the OS pages state in and out of the context window with 99% efficiency.

The Sidecar Compiler

AgentCTX is a compiler, not an LLM.

Instead of relying on unpredictable LLM middleware, AgentCTX uses a deterministic Rust compiler (the sidecar) to parse agent commands into 7 distinct target formats:

  • SurrealQL: For vector search, memory, and analytics
  • REST & GraphQL: For legacy API integration
  • MCP JSON-RPC: For native Model Context Protocol tools
  • CTXB: Binary machine-to-machine transport encoding

Every translation is cryptographically signed using Ed25519, creating an immutable, verifiable audit trail of what the agent actually saw and did.

The Architecture

6 tiers. Zero bloat. Every layer earns its place.

Agent Tier
AI AgentLLM Runtime
CTXAgent Query Language
Control Tier
GatewayZero-Trust Router
IdentityAgent Registry
OrchestratorAgent Loop State Machine
Compiler Tier
Sidecar CompilerDeterministic · Ed25519 Signed · Compiler not LLM
Context Tier
7 Context PlanesStructured Agent State
Audit TrailVerifiable Trust Record
Storage Tier
SurrealDB 3.0Multi-Model Database
Human Boundary
Interface Tier
SDKDeveloper
CLIOperator
Web UIAdmin
AnalyticsObservability

Full-Stack Compression

Bigger context windows are compounding debt. CTX is compounding value.

Input Plane (k/t/s)
91%Fewer Tokens
12,000 → 1,100 tokens
CTXJSON
Output Plane
76%Fewer Tokens
850 → 200 tokens
CTXJSON
Response Plane (CTX)
76%Fewer Tokens
JSON → CTX Encoding
CTXJSON
Coordination (CTXB)
99%Fewer Tokens
2,000 → 15 tokens
CTXJSON

Comprehensive Control

View All 100+ Features & Roadmap →

Seven Context Planes

Tools, knowledge, memory, skills, agents, inspection, LLM — one unified cryptographic gateway.

5.7× Token Compression

Measured across 12 operation types, not theoretical limits.

Persistent Memory

Cross-session, tag-filtered, sub-ms lookup flat to 50,000 entries.

MCP-Native Proxy

Lazily spawned, role-scoped, namespaced. Zero vendor lock-in.

8-Layer Security

From WASM parse-time validation to distributed Threshold Crypto.

Agent-to-Agent

15 tokens per protocol message vs 2,000+ tokens in prose manifests.

Signed Translations

Every action has an Ed25519 deterministic cryptographic receipt.

Rust Multi-Lang Core

TypeScript foundation + Rust parser (Node.js, WASM, Python, native binaries).

Convergent Deduplication

O(1) storage scaling across large fleets. 100 agents securely discover and deduplicate identical semantic insights.

Automation Engine

Run scheduled background tasks, stateless cron agents, and complex DAG workflows without human-in-the-loop dependencies.

Sentinel Alignment

Strictly enforce groundedness with pre/post execution hooks. Detect divergence, anomalies, and sandbagging across the fleet in real-time.

Deployment Tiers

From local open-source testing to enterprise-scale autonomous swarms.

Free (Local Open Source)

Price$0 / month
Capacity1 Local Agent

Full Apache-2.0 CLI, local encrypted credential storage (BYOK + 1Password), L1 compaction, Ed25519 signing, and local SurrealDB. 1-agent limit enforced via WASM compilation boundary.

Perfect for local scripting and personal AI assistants.

Developer Action:npm create agentctx@latest
"Every MCP gateway routes traffic. Only AgentCTX optimizes what agents know."
Capability Infra Tools AgentCTX
MCP Routing
Input Compression 91% savings
Output Compression 76% savings
Response Compression CTX 25-76%
Persistent Memory <1ms recall
Multi-Agent Coordination 15 tokens
Cryptographic Trust Ed25519
OS-Level Isolation RBAC + scope
Read Full Comparison Matrix

Terminal Velocity

Configure the entire context stack in five commands.

~/project
$

Ready to restore agent autonomy?

Start saving tokens and gaining cryptographic trust in your agent workflows today.