Skip to content

Introduction

AgentCTX is a cognition layer for AI agents. It gives every agent — Claude, Gemini, GPT, Llama, or whatever comes next — structured memory, scoped tool access, semantic knowledge retrieval, and cryptographically verifiable trust, all through a single gateway and a purpose-built query language called CTX.

Every session, your agent starts empty. No memory of yesterday. No recall of the tools it used, the bugs it fixed, or the architecture it debated for hours. It re-reads files, re-discovers tool schemas, and reconstructs understanding from scratch.

This costs you tokens, time, and quality:

Waste CategoryWithout AgentCTXWith AgentCTXSavings
Tool descriptions (70 tools)9,950 tokens850 tokens91%
Tool invocations (150 calls)7,350 tokens1,800 tokens76%
File search + read16,925 tokens1,290 tokens92%
Swarm coordination21,000 tokens860 tokens96%
Cross-session resumption6,500 tokens214 tokens97%
Total per session96,645 tokens8,161 tokens91.6%

That freed context window isn’t just cheaper — it lets your agent think. More room for reasoning, fewer hallucinations, longer autonomous runs.

AgentCTX introduces CTX — the first query language designed for how agents actually process information. Instead of verbose JSON-RPC or natural language, agents write structured operations:

?k "auth" #code @7d ^3 search knowledge (9 tokens, was 46)
>t github.issues.create title="Fix SSE" call a tool (25 tokens, was 67)
+m auth-decision #arch "JWT for API" store a memory (12 tokens, was 49)
?s "process assets" ^3 recommend skills (8 tokens)

Every operation flows through one gateway and targets one of seven planes:

PlaneSymbolPurpose
ToolstDiscover, inspect, and call MCP tools
KnowledgekSemantic search across ingested documents
Memorym5-layer persistent memory with decay and consensus
SkillssReusable workflows and agent capabilities
AgentsaMulti-agent coordination and delegation
InspectioniRuntime introspection of the CTX system
LLMlDirect language model inference and embedding

Every action an agent takes through AgentCTX produces a signed audit trail. The sidecar translator converts structured CTX into human-readable markdown, signs it with Ed25519, and logs it. No LLM in the translation path. No hallucination risk. Run actx verify and the math settles any dispute.

Agent writes: +m "decision" #arch "JWT for API, session tokens for WebSocket"
Human reads: "Stored architecture decision: JWT for API, session tokens for WebSocket"
Signature: Ed25519 signed — verifiable with `actx verify`
  • Agent developers building tools, frameworks, or autonomous systems
  • Platform teams operating multi-agent deployments at scale
  • Enterprise teams that need verifiable audit trails for AI operations
  • Anyone tired of watching agents waste 90%+ of their context window on tool schemas they’ve already seen