Papers
Memagen™ research notes.
Long-form writeups of how Memagen™ works. Master paper covers the whole platform; specialty papers go deep on individual subsystems. Each is published as both a web page and a downloadable PDF.
Master paper
Specialty papers
-
AutoMCP: Inferring Parametric Macros from Typed Action Graphs
Observe agent tool-use, propose named macros, promote stable patterns to first-class tools
AutoMCP is the macro-inference layer in Memagen™ Lite. It observes agent tool-use, recognizes repeated structural patterns in the typed action stream, and proposes parametric macros for user approval.…
-
UIMCP: Adaptive Catalog Compression for Multi-Tool Agent Dispatch
How Memagen™ encodes a 90-command catalog (sourced across three framework adapters) into 42.7x fewer tokens per turn without measurable loss in tool-selection quality
Production agent platforms inject every available tool's full schema into the LLM context on every turn, paying a token tax that scales linearly with catalog size. With a typical native tool-use schem…
-
The Compound-Graph Substrate as Live Visualization: Recording, Anonymizing, and Replaying a Real Agent's Memory in Three Dimensions
How the Memagen™ v4 hero captures real graph mutations from a running agent and projects them, unfaked, into a 3D scene that doubles as a debugging instrument
The Memagen™ marketing site visualises the platform's compound-graph memory in three dimensions on the landing page. The visualization is not a hand-authored animation. It is the deterministic playbac…
-
AutoWebMCP: Automatic MCP Tool Schema Generation from Arbitrary Web Pages
Forms, links, OpenAPI/Swagger sniffs, and SSRF-protected fetches — turning any URL into a runnable agent tool
Every web application is, in principle, an agent tool: it accepts inputs, performs an action, and returns a response. In practice agents cannot use arbitrary websites because they lack a schema descri…
-
Default-Restrictive Safety Toggles with Hard Invariants: A User-Controllable Framework for AI Agent Capability Boundaries
Twenty toggles, eight invariants no toggle can bypass, and a UX that prices loosening transitions higher than tightening ones
We describe the safety-toggle framework that ships in Memagen™ Lite (V1-lite, MIT). Every dangerous capability the platform exposes — auto-sending email, auto-pushing code, lifting the outbound-networ…
-
PCMCP: A Polymorphic Compound MCP for Unified Agent Tool Surfaces
Merging UIMCP, AutoMCP, AutoWebMCP, and accessibility-tree desktop control into one namespace with capability inheritance and per-tool gating
Production agent stacks accumulate MCP surfaces faster than they can manage them: a catalog-compression layer (UIMCP), an inferred-macro layer (AutoMCP), an auto-generated-from-the-web layer (AutoWebM…
-
The V3-P Capability Vault: Per-Use Grants and Graph-Walked Audit Chains for LLM Agent Tool Surfaces
Fernet-encrypted credential storage, time-bounded scope-bounded grants, and an audit trail that is itself a queryable graph
Most agent frameworks treat tool access as a binary per-server toggle or as a trust-based decision the model is allowed to make. Both shapes fail when the tool surface includes credentials whose leak …
-
Multi-Provider LLM Routing for Tool-Calling Agents: A Provider-Abstraction with Lenient-Parser Splice Points
Routing, failover, per-agent override, and the ContextVar-based splice point that makes the lenient parser provider-aware
Most current agent platforms hard-code a single LLM provider — typically OpenAI or Anthropic — and pay the resulting tax in rate limits, billing concentration, geographic constraints, and model availa…
-
Lenient Tool-Call Parsing: Bridging Weak-Tool-Call Models to Native Tool Catalogs
Memagen™ recovery of tool calls across four production-observed emission patterns, per-tool argument coercion, and hallucinated-result detection
Production agent runtimes enforce strict tool-call shapes — JSON Schema, OpenAI-style function calling, Anthropic-style tool_use blocks — and reject model output that fails validation. The contract is…