Project Brain: Start with
shared knowledge.
Ground each agent in project sources, reviewed decisions and code impact before it edits.
Explore Project BrainThe persistent,model-agnosticharness forcoding agents.
Ground coding agents in shared project knowledge. Save plans and checkpoints. Validate changes, review evidence and control integration.
Project context for the tools you already use
From project knowledge
to controlled integration.
Your model reasons and uses its tools. Snipara supplies project knowledge and controls the configured workflow.
Context
Load project sources, reviewed memory and code impact.
Plan
Define the plan, phases and scoped tasks.
Execute
Run tasks through the configured model and adapter.
Validate
Run external checks and retain the evidence.
Review
Have a separate reviewer inspect the candidate.
Integrate
Apply configured acceptance gates before integration.
MCP context access and native execution support are different. Native execution depends on the configured adapter, policy, model endpoint and permissions.
How the harness worksA model writes code.
One harness. Three connected layers.
Three layers connect what your agents know, what they do and what gets reviewed.
Project Brain: Start with
Companion: Continue from
the work already done.
Resume work from saved checkpoints. Keep plans, phases, tasks, attempts and evidence for the next agent.
Explore CompanionOrchestrator: Keep review
in the workflow.
Run configured execution, separate review and controlled integration. Keep evidence alongside the decision.
Explore OrchestratorYour coding tools.
One Snipara plugin.
Install Snipara in Claude Code or Codex. Connect your account, choose your project and ask for an answer you can check.
Snipara, Companion and Orchestrator are enabled by default in the native plugin, with independent on/off settings. Local engines require explicit setup; enabling a module does not start execution. The plugin is free, with a Snipara account required. Service plans are separate.
Continue from a checkpoint.
Save the state of the work, resume the next phase and keep the review decision separate.
A saved-checkpoint example
Interactive illustrationClaude CodeEarlier work savedProject checkpoint
- Plan and decisions
- Preserved
- Completed tasks
- Preserved
- Attempts and evidence
- Preserved
- Next phase
- Ready to resume
A fresh Codex sessionReady for the handoffYour work has a place to return to.
Save the plan, completed tasks, attempts and evidence before the next session.
Illustrates the workflow, not a live run. Resume requires the project folder, saved artifacts and the project’s Snipara MCP.
The agent can change.
The work continues.
In one local demonstration, Claude Code completed the first two phases. A fresh Codex session resumed the saved checkpoint and continued. The demonstration passed 21 independent validation cases.
Inspect the handoff evidence- Plan and decisions
- Preserved
- Original evidence
- Preserved
- Validation
- Outside the coding session
10 October 2026. Operator-reported local proof.
What this demonstrates
One shared workspace and one fixture. Resume used local .snipara state, project files, referenced artifacts and the project’s hosted Snipara MCP. This does not establish live-process migration, MCP-only recovery, general reliability or time and cost savings.
Read the public receiptBefore you connect.
How do I install Snipara in Claude Code or Codex?
Install the free native plugin from Snipara’s publisher marketplace, connect its MCP server with OAuth and choose your Snipara project. Snipara, Companion and Orchestrator are enabled by default and can be switched off independently. Local engines require explicit setup and do not start automatically. A Snipara account is required; optional service plans are purchased separately. Official directory submissions are in preparation. Installation instructions are at snipara.com/plugins.
Can Claude Code work be resumed by Codex?
Companion can resume saved workflow state when the next coding tool has access to the project folder with its saved .snipara state and artifacts, and the project’s Snipara MCP. One local Claude Code to Codex test preserved the plan, completed tasks, attempt counters and evidence, then passed 21 independent checks. This is checkpoint continuity, not migration of a live process. MCP-only restoration and Orchestrator controller transfer were not tested.
What is Snipara?
Snipara is a persistent, model-agnostic harness for coding agents. It combines project context and reviewed memory with Companion workflows and Orchestrator execution, external validation, independent review and controlled integration.
What is a coding agent harness?
A coding agent harness is the system around a model that supplies context, scopes its work, manages execution and checks changes. The model proposes code; the harness defines the workflow and the conditions for accepting it.
Does Snipara replace Claude Code, Codex, Cursor, or ChatGPT?
Your model and coding client still reason and use tools. Snipara supplies project knowledge and workflow controls. MCP context access and native execution support are different capabilities; native execution depends on the configured adapter.
How is Snipara different from a context tool?
Context and memory ground the work. Companion tracks the plan and phases; Orchestrator can execute bounded tasks and bind validation and review to a candidate before controlled integration. A passing test alone does not approve a change.
Which configurations have been tested?
An isolated Claude CLI journey reached acceptance with a test-local launcher. Qwen3 Coder Next through LM Studio passed external validation, then independent review refused a defect and blocked integration. These tests use one exposed development fixture and do not establish general model reliability.
Your models.
Your project harness.
Connect the tools you already use.
Give the work a place to continue.