Percept · v1.5.8

Percept

Three modules that turn VEKTOR into an ambient intelligence layer — surfacing what you were working on, processing files you drop into an inbox, and running interactive thinking sessions with full memory access. Shipped in v1.5.8.

Percept Chat Layer

A session intelligence layer that plugs into the VEKTOR REPL (vektor-percept-chat.js). Instead of passively waiting for queries, it watches what you type and surfaces related memory at natural pause points — like a colleague who quietly tracks context without interrupting.

vektor-percept-chat.js Session Layer

Capabilities

FeatureDescription
Morning HandoverOn startup, surfaces yesterday’s active topic thread, where you left off, and any new web signals relevant to that thread.
Progressive Idea SurfacingAccumulates a topic buffer as you type. At natural pause points surfaces 1–3 related memories as soft hints that deepen if the topic sustains.
Step TrackerDetects multi-step tasks (code, research, trademark filing) and shows current step inline with auto-saved progress.
Idea ExpansionThree depth levels earned by engagement: Whisper, Bloom, Anchor. Fades gracefully when topic shifts.
Web Signal SurfacingIf a new percept signal matches the active topic, surfaces it as a quiet inline link without interrupting flow.

Depth Levels

Depth is earned by engagement — never triggered automatically. The system only goes deeper when you go deeper.

LevelNameOutput
1WhisperSingle concept word, barely visible. First hint that a memory is near.
2BloomShort phrase, one connection. Surfaces when topic sustains across turns.
3AnchorSynthesised insight, held until topic shifts. Only reached with deep engagement.

Usage (in vektor-repl.js)

javascript
const PerceptChat = require('./vektor-percept-chat');
const pc = new PerceptChat(mem, cfg, llmCall);
await pc.morningHandover();        // call after banner()
pc.onInput(userText);              // call on every line input
const hint = await pc.getHint();   // call after each LLM reply
if (hint) process.stderr.write(hint + '
');

Design Principles

PHILOSOPHY
Never interrupt flow. Surface only on natural pauses. One thing at a time. Warm, not creepy — “we were working on X” not “I know X”.

Percept Inbox Daemon

Background daemon (vektor-percept.js) that watches ~/.vektor/inbox/ for dropped files and auto-processes them into MAGMA memory without any user action. Drop a file, walk away — it handles extraction, synthesis, and storage.

vektor-percept.js Daemon CLI

Supported Formats

ExtensionHandling
.txt  .mdPlain text and Markdown notes — full synthesis pipeline.
.jsonStructured memory arrays or note objects — direct ingestion.
.transcriptMeeting or voice transcripts — chunked and summarised.
.logLog files — chunked at 3,000 chars, each chunk summarised independently.

Processing Pipeline

Per file: detect type → extract text → LLM synthesis (title, summary, entities, decisions, actions, tags) → store structured note + memory fragments in MAGMA → move to done/. Failed files move to error/ with a processing receipt alongside each file.

Drop Zones

bash
~/.vektor/inbox/          # drop files here
~/.vektor/inbox/done/     # processed files moved here
~/.vektor/inbox/error/    # failed files moved here
~/.vektor/inbox/percept.log  # processing log

Commands

bash
vektor percept               # start daemon (blocks)
vektor percept --once        # process inbox once then exit
vektor percept --dir <path>  # watch custom directory
vektor percept --no-llm      # heuristic extraction only, no LLM cost
vektor percept status        # show inbox stats

Configuration

json
// ~/.vektor/config.json
{
  "percept-provider":      "groq",     // groq | ollama | openai | claude
  "percept-session-model": "llama-3.3-70b-versatile",
  "percept-fast-model":    "llama-3.1-8b-instant"
}

Percept Worker CLI

Standalone thinking-loop CLI (percept.js) for interactive session-based memory work. Provider-agnostic across 14 providers. Separate fast model for worker and distillation passes, session model for conversation. Full MAGMA memory access throughout.

percept.js CLI

Supported Providers

Groq, Ollama, OpenAI, Claude, Mistral, Together AI, OpenRouter, Cohere, xAI / Grok, DeepSeek, LM Studio, MiniMax, NVIDIA NIM, Perplexity.

In-session Commands

bash
/insights [days]    # briefing of last N days (default 7)
/recall <query>     # search memory directly
/remember <text>    # store a memory manually
/status             # show memory DB health

Configuration

json
// ~/.vektor/config.json
{
  "percept-provider":      "groq",
  "percept-session-model": "llama-3.3-70b-versatile",
  "percept-fast-model":    "llama-3.1-8b-instant",
  "ollama-host":           "http://localhost:11434",
  "ollama-model":          "llama3.2"
}

Environment Overrides

bash
PERCEPT_PROVIDER=claude
ANTHROPIC_API_KEY=sk-...
GROQ_API_KEY=gsk_...
OPENAI_API_KEY=sk-...
FULL FEATURE ARTICLE
A detailed walkthrough of all Percept features — Morning Handover, Whisper/Bloom/Anchor depth system, Inbox Daemon, Step Tracker, and Web Signal Surfacing — is coming to the blog. View blog