Honcho Theory-of-Mind & Cognitive User Profiler

@plastic-labs/honcho · v1.0.3

A Theory-of-Mind cognitive profiler for DeepSeek Harness agents. Dynamically infers unstated user intents, programming habits, and evolving preferences across long-term collaborative sessions.

Theory-of-MindCognitive-MemoryUser-ProfilerEmpathy
GitHub Stars
20 K+
+12.4% this month
Monthly Downloads
78 K+
Monthly registry pulls
Reach Score
97.4/ 100
Top Tier Ecosystem
Runtime
Cordis v3+
Node 18+ / Bun / Deno

Installation & Integration

CLI one-click launch, package managers, and Cordis integration

bash
manager:
$ pnpm add @plastic-labs/honcho

Architecture

Honcho Memory moves beyond rudimentary vector similarity search to build genuine cognitive resonance. Traditional memory stores recall text chunks without understanding the engineer's technical mindset, architectural biases, or underlying frustrations. Integrating cognitive Theory-of-Mind modeling into Cordis, Honcho maintains a live dialectical model of the user. It anticipates unstated architectural constraints, personal coding heuristics, and domain proficiencies, allowing agents to respond with intuitive empathy and precision.

Architectural Principles & Constraints

01
Strict Type Isolation

Guaranteed by TypeScript compile-time contracts, inter-plugin event bus calls enjoy zero-drift safety.

02
Sub-Millisecond Hot Reload

Supports dynamic runtime mounting and graceful unloading without restarting the primary host process.

03
Deterministic State Machine

Embeds multi-phase execution lifecycle guards, preventing context loss during long-horizon reasoning.

04
Zero Native Build Dependencies

Designed for lightweight cross-platform environments, booting instantly across Node.js, Bun, and Deno.

Core Features

01
Theory-of-Mind Modeling: Discovers unstated intentions behind ambiguous developer prompts
02
Code Taste Alignment: Adapts to user conventions regarding functional idioms, naming, and types
03
Adaptive Expertise Scaffolding: Tailors architectural depth to junior, senior, or staff levels
04
Evolving Cognitive Tree: Compounds collaborative rapport without robotic fact regurgitation

Core Workflow

01

Implicit Cue Extraction

Extracts implicit communication patterns, preferences, and corrections from turns.

02

Hypothesis Synthesis

Synthesizes probabilistic hypotheses regarding user skill level and technical taste.

03

Cognitive Graph Update

Reinforces verified traits in the user profile while discarding refuted hypotheses.

04

Adaptive Tone Steering

Injects empathetic mental models to tailor explanation depth and coding style.

Configuration Parameters Reference (YAML / JSON)

ParameterTypeDefaultDescription
inferenceConfidencenumber0.75Confidence threshold to solidify user trait
privacyModebooleantrueStrict user privacy isolation and anonymization
maxUserTraitsnumber50Maximum cognitive traits retained per user

Use Cases

Enterprise Production Agent

Relies on microkernel lifecycle guards and fault-tolerant state machines for continuous reliability.

SWE-bench Benchmark Evaluation

Native integration with SWE-bench workflows, automatically capturing diffs and verification metrics.

Autonomous Code Refactoring

Separates reasoning from tool actions to independently locate and refactor multi-file codebases.

Cross-Tool Workflow Automation

Safely orchestrates events across sandboxes to seamlessly link enterprise developer tooling.

Best Practices

01
Sandbox Permission Guard

Strictly isolate sub-process calls and network scope; deploy within Docker containers in production.

02
Exponential Backoff Retries

Configure adaptive exponential retries with strict timeouts to mitigate upstream model rate limits.

03
Session State Checkpointing

Persist state machine snapshots to survive hardware interruptions and resume instantly without loss.

04
Full Trajectory Audit Logs

Enable full trace logging, aggregating reasoning thought streams and tool I/O into your observability hub.

FAQ

Q1:How to handle timeouts in long-running autonomous tasks?

Increase the timeout parameter inside your YAML configuration and dispatch periodic heartbeat signals across the Cordis event bus. For long-running tool execution and model reasoning, configure persistent session snapshotting so suspended tasks can safely resume their exact context after interruptions, preventing the kernel from recycling active agent sessions prematurely.

Q2:How to capture and stream the model reasoning thought process?

The harness runtime natively provides end-to-end streaming hooks while its state machine automatically intercepts and strips <think> reasoning tags from model responses. Subscribe directly to the onThink event listener to consume live reasoning token streams in real-time, delivering typewriter animation to the user interface while persisting full trajectories for audit compliance.

Q3:How to resolve dependency conflicts across multiple plugins?

Cordis microkernel uses directed acyclic graph topological sorting to dynamically resolve plugin dependencies. When shared services or runtime versions conflict, assign distinct isolated namespaces at the application entrypoint. Leveraging context injection alongside lazy activation ensures dependencies load strictly on-demand when tools are triggered, maintaining system stability and preventing memory bloat.

Q4:How to enforce permissions and sandbox isolation in production?

Combine isolated container sandboxing with fine-grained capability checks to prevent plugins from accessing sensitive files or unauthorized external networks. Enforce explicit runtime system call whitelisting through the microkernel, executing all third-party tool scripts inside isolated ephemeral containers to block arbitrary code execution and eliminate security privilege escalation risks entirely.

Recommended Ecosystem Plugins

Explore related Cordis extensions designed to work synergistically