Skip to content

Praxist

Praxist coordinates parallel research agents, experiments, evidence retention, and synthesis across generations. It supplies the reusable research process; your task project supplies the science.

Read the technical paper, Praxist: From Experimental Artifacts to Solution Lineages, for the system design and evaluation.

A generation inherits frontier, agenda, and Gems; allocates parallel peers that build artifacts; evaluates those artifacts into typed findings; and synthesizes findings into a frontier update and the next agenda, which the following generation inherits. Artifacts, findings, decisions, and agendas accumulate into a lineage DAG that explains the final artifact.

Parallel work becomes measured evidence, durable research state, and a focused agenda for the next generation.

Research Infrastructure, Explicit Science

A coding agent is the recommended interface between the researcher and two deliberately separate systems.

flowchart LR
  HUMAN(("Researcher"))
  AGENT(["Codex / Claude Code<br/>recommended interface"])
  PRAXIST["Praxist<br/>generic research process"]
  TASK[["Task project<br/>scientific contract"]]

  HUMAN --> AGENT
  AGENT --> PRAXIST
  AGENT --> TASK
  PRAXIST <--> TASK

  class HUMAN actor
  class AGENT interface
  class PRAXIST system
  class TASK task
Praxist owns The task project owns
Peers, generations, orchestration, resource scheduling, and lifecycle Objective, constraints, baseline, environment, and permitted changes
Agent runtimes, evidence transport, durable state, replay, and synthesis Evaluator, metrics, protocol, evidence maturity, prompts, and roles

The boundary keeps Praxist reusable across fields and makes the task project the sole source of domain meaning. Architecture defines the software boundary; Task Projects defines the scientific contract.

Install Praxist

Install and configure Praxist with one command:

python3 -m pip install --index-url https://pypi.org/simple "praxist[agents,codex]" && praxist setup --interactive --install-skills codex

Or let an agent install from PyPI and follow the packaged setup runbook:

codex --yolo
# or: claude --dangerously-skip-permissions
Install and configure Praxist using its packaged OOBE runbook. Stop after readiness checks.

Installation never selects a project or starts research. Before the separate takeover step, read the Quickstart and Your First Task. The selected project must already contain the code and local resources needed to run its baseline; Praxist does not invent missing data, simulators, credentials, or measurements.

Choose A Runtime Profile

Continue After Setup

  • Prepare a research task

    Define the research brief, prerequisites, and launch gates.

    Your first task

  • Operate from the shell

    Use the direct CLI for lifecycle and monitoring operations.

    Direct CLI operations

The Research Brief Is the Control Surface

Takeover can inspect code and measure an existing baseline, but it cannot infer the researcher's priorities. The brief should identify the objective, credibility standard, allowed resources, exploration policy, and practical run budget. Those decisions shape research direction, experiment throughput, and retention from the first generation onward.

Your First Task provides a complete example and explains how takeover turns that brief into a validated task project.

Find a Specific Answer

You want to... Start here
Install and configure Praxist Installation
Complete setup and hand off a project Quickstart
Understand project prerequisites Your First Task
Use agent workflows Agent Skills
Diagnose a failure or stall Troubleshooting
Understand the research loop Research Loop
Configure a task harness Task Projects
Choose a scaffold or complete reference Examples And Templates
Inspect a complete Python/JAX project Rocket Booster Recovery
Inspect a complete native Rust project Rocket Booster Recovery (Rust)
Extend Praxist Developer Guide
Look up an exact command CLI Reference

The Documentation Policy identifies the sole owner of each contract.