Saccadic is a deployable Cognitive Resonance Artifact from OkeyMeta Ltd. It is built for people who want to run a portable AI system, connect their own tools, and host it anywhere without cloning the private architecture repository. No private repository checkout is required.
Mission
SLE is a CPU-first path toward artifact-native intelligence: learned state that can move across machines, run close to users, and use external tools without turning the host application into a hidden model. The goal is simple for builders: ship model.cra, start Spark, and let Saccadic expose what it selected, argued, remembered, and generated from loaded artifact state.
Saccadic Highlights
SLE replaces parameter-count thinking with portable cognitive state. The artifact is the model.
No tokenizer. No Transformer stack. No private repo checkout.
Spark is a runtime boundary, not a hidden second model. It loads the artifact, executes declared modes, and returns loaded-state evidence.
Raw text and raw acoustic input are processed through predictive stream dynamics instead of BPE tokenization or speech-to-text.
Host tools are executable boundaries. Saccadic selects learned tool paths, emits arguments, consumes returned values, and speaks through artifact state.
SLE names releases by cognitive capacity notation, not parameter count.
Saccadic is designed for personal assistants, workflow agents, private services, edge systems, desktop apps, and embedded hosts that need a portable AI boundary.
What You Can Build
Conversational assistants that carry recent chat history into the artifact runner.
Workflow agents that select learned tool names and emit auditable argument maps.
Private customer, operations, research, or device copilots that keep host services as executable boundaries.
Edge, desktop, and container deployments where model.cra and Spark move together.
OpenAI-compatible chat services for teams that already use SDK-based application code.
Model Overview
Field
Value
Release
SLE-V2.1-Ω12K-LX
Hugging Face slug
SLE-V2.1-Omega12K-LX
Model name
Saccadic
Architecture
Saccadic-Liquid Engine (SLE)
Public artifact
model.cra
Spark runtime
sle_spark.py
Metrics
sle_v2_1_release_metrics.json
Requirements
requirements.txt
Selected training rows
502,000
Curation failures
0
Deployment targets
cli, service, edge, desktop, container
This package includes model.cra, Spark, requirements metadata, release metrics, the release manifest, and generated host boundaries. The private source repository is not required to run Saccadic.
Quickstart
Download this Hugging Face model package and keep the files together. The public runtime is OpenAI SDK-compatible: start Spark, point the SDK at the local service, and call client.chat.completions.create.
Spark exposes POST /v1/chat/completions behind the local /v1 base URL.
Create one chat.py beside model.cra and sle_spark.py:
python
1from openai import OpenAI
23client = OpenAI(4 base_url="http://127.0.0.1:8765/v1",5 api_key="not-needed",6)78messages =[9{"role":"system","content":"Reply naturally and use the latest user turn."},10{"role":"user","content":"Hello! Tell me about yourself."},11]1213stream = client.chat.completions.create(14 model='SLE-V2.1-Ω12K-LX',15 messages=messages,16 stream=True,17 extra_body={"max_speech_steps":18},18)1920answer =[]21evidence ={}22for event in stream:23 piece = event.choices[0].delta.content or""24print(piece, end="")25 answer.append(piece)26 extra =getattr(event,"model_extra",{})or{}27 evidence = extra.get("saccadic", evidence)28print()2930messages.append({"role":"assistant","content":"".join(answer)})31print("tool path:", evidence.get("tool_path"))32print("final value:", evidence.get("final_value"))
Expected shape: normal streamed chat text first, then optional loaded-artifact evidence. For arithmetic, tools, facts, and system-instruction turns, the saccadic evidence shows selected tool paths, emitted arguments, final values, slot transfers, and replay evidence.
To bind your own tool, keep the same OpenAI SDK call and add extra_body={"host_tools": ["artifact.tool_name=your_module:your_function"]}. Spark executes that callable only if model.cra selects the learned tool name and emits arguments from artifact state.
Place model.cra, sle_spark.py, SLE_RELEASE.json, and any declared metrics or requirements metadata in one directory. Then run python -m pip install -r requirements.txt from that directory. The runtime command below is the public boundary; users do not install this private repository.
Direct CLI
Most applications should use the OpenAI-compatible service above. The direct CLI remains available for diagnostics and returns the same loaded-artifact evidence from model.cra.
Edge And Desktop
Use the generated host files when included:
powershell
1python edge_host.py
2python desktop_host.py
Both read JSON payloads from stdin, forward declared host tools to the shipped runtime, and print loaded-artifact evidence.
Raw Acoustic Input
Raw acoustic runs pass waveform samples directly; there is no speech-to-text or tokenizer layer:
Keep model.cra, Spark, requirements.txt, SLE_RELEASE.json, and any metrics files in the same deployment directory.
Use --avoid-replay for public demos so exact source-row echoes are surfaced as evidence instead of mistaken for intelligence.
Bind host tools with --host-tool artifact.name=module:function; the host executes tools, while Saccadic selects paths and emits arguments from loaded artifact state.
Spark includes documented portable primitives for math.add and math.power; external tools still use explicit host bindings.
Pass recent conversation as raw text in history mode when you want Saccadic to respond to prior turns.
Inspect returned JSON fields such as selected tool paths, emitted arguments, final values, stream dynamics, punctuation symbols, slot transfers, and replay evidence.
Trust And Evidence
Saccadic is an artifact-first release: supported response, history, autonomous, action, acoustic, and system-instruction paths return loaded-state evidence rather than hidden host-written answers. Evidence includes tool paths, emitted arguments, final values, autonomous route records, context transfers, punctuation symbols, Speech Cortex usage counts, system-instruction records, fact attributes, slot transfers, emitted exact-row replay evidence, and blocked replay evidence.
Training And Selection
Selected rows: 502,000
Curation failures: 0
Training Domains
arts: 20,080
biology: 20,080
chemistry: 20,080
constitution: 20,080
conversation: 20,080
economics: 20,080
emoji: 20,080
geography: 20,080
history: 20,080
language_es: 20,080
language_fr: 20,080
language_ha: 20,080
language_ig: 20,080
language_yo: 20,080
language_zh: 20,080
law: 20,080
math: 20,080
medicine: 20,080
philosophy: 20,080
physics: 20,080
safety: 20,080
stories: 20,080
system_instruction: 20,080
technology: 20,080
world: 20,080
Citation
bibtex
1@software{sle_saccadic,
2 title = {Saccadic-Liquid Engine: Saccadic Cognitive Resonance Artifact},
3 author = {OkeyMeta Ltd},
4 version = {SLE-V2.1-Ω12K-LX},
5 note = {CPU-first Cognitive Resonance Artifact with Spark runtime}
6}
