- Builders experimenting with persistent agent context
- Teams that want a lightweight memory companion to agent skills
- Developers comparing memory approaches for coding agents
Skills
GBrain
Open context and memory layer for giving agents a more durable project brain.
MIT License
garrytan Maintainer
2026-04-19 Verified
Overview
What is GBrain?
GBrain is an open project around structured agent memory and context, useful for builders exploring how agents can preserve working knowledge across sessions.
Agent context focus
GBrain is oriented around memory and reusable context rather than a single task prompt.
Persistent context is one of the practical blockers for reliable agent delegation.Pairs naturally with skills
Memory becomes more useful when combined with repeatable agent workflows.
The combination gives agents both procedure and recollection.Open inspection path
The repository gives builders a way to study and adapt the approach.
Memory systems need trust because they shape future agent behavior. Use cases
What GBrain is built for
01
Project memory
Store durable notes about architecture, conventions, and decisions for future agent sessions.
02
Skill augmentation
Combine workflow skills with remembered project context.
03
Agent handoffs
Use structured context to make agent-to-agent or session-to-session continuity less brittle.
Quick start
Get started in seconds
$
git clone https://github.com/garrytan/gbrain.git Comparison
How it stacks up
GBrain is closer to context infrastructure
vs prompt snippetsPrompt snippets help in the moment; GBrain-style context is about what an agent can carry forward.
FAQ
Frequently asked questions
What should I check before using GBrain?
Evaluate GBrain by reading its official source, then running one workflow end to end. Check when the skill should be invoked, what inputs it expects, what evidence it collects, and how easy it is to edit or version.
Is GBrain open source?
GBrain is listed with MIT based on the official source links in this profile. Re-check the repository, model card, or docs before production use.
Who should evaluate GBrain?
GBrain is most worth evaluating for builders experimenting with persistent agent context.
Decision brief
JSON
Should you use GBrain?
- Users who want a fully managed consumer product with no setup work
- Teams that cannot review the linked source, license, and operational requirements before adoption
- Verified 2026-04-19
- License: MIT
- Repo: garrytan/gbrain
- Open-source signal
Deployment
Check source
Permission surface
shell/files, memory
Decision signals
No extra signals recorded
Agent packet
Structured decision data for GBrain
This packet is the compact machine-readable view agents should use before following source links or taking action.
Capabilities
agent skill, memory, context retrieval, state management
Constraints
open source
Deployment
Check source
Permission surface
shell/files, memory
Recommended workflows
Coding agent workflow, Memory or RAG workflow, Reusable skill workflow
Overview
What GBrain does
What it is
GBrain is an open agent skill resource: a reusable procedure, instruction pack, or capability layer that should make an agent better at a repeatable task than one-off prompting.
Why it matters
GBrain matters because agent work breaks down when context disappears. A durable project brain can help agents keep track of decisions, preferences, and reusable project knowledge.
How to evaluate it
Evaluate GBrain by reading its official source, then running one workflow end to end. Check when the skill should be invoked, what inputs it expects, what evidence it collects, and how easy it is to edit or version.
Facts
Known metadata and operating surface
These fields are separated from editorial interpretation so agents can reason over facts and missing checks.
Resource type skill
Category Skills
Maturity active
Difficulty Unknown
License MIT
Pricing open source
Verified 2026-04-19
Source confidence medium
Risk level elevated
Fit matrix
Where GBrain fits in an agent stack
strong
Coding agent workflow
GBrain has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning.
- Run a small repository change and inspect the diff, tests, and rollback path.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
strong
Memory or RAG workflow
GBrain has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning.
- Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
strong
Reusable skill workflow
GBrain has multiple signals for reusable skill workflow, including matching tags, capabilities, category, or positioning.
- Run one skill end to end and check whether it produces evidence or structured output.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial
Evaluation and observability
GBrain has at least one signal for evaluation and observability, but should be checked against a real task before adoption.
- Add one repeatable test case and confirm results can run again in review or CI.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak
Browser automation
GBrain is not primarily positioned for browser automation in the current metadata.
- Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak
Connector or protocol layer
GBrain is not primarily positioned for connector or protocol layer in the current metadata.
- Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
Inputs and outputs
What an agent should inspect
Likely inputs
- Repositories, files, issues, terminal output, and test results
- Documents, user facts, entities, context, or retrieval queries
- Official setup instructions and a small real workflow
Likely outputs
- Diffs, commits, explanations, test results, or review notes
- Retrieved context, memory updates, graph relations, or citations
- Scores, traces, regression results, dashboards, or failure cases
- A decision on whether this resource fits the target workflow
Evidence
Sources, claims, and missing checks
Claims are marked separately from source links so future crawlers and reviewers can update them without rewriting the page.
GBrain is listed as open source.
License metadata: MITGBrain has a recorded GitHub repository: garrytan/gbrain.
Resource facts and GitHub source link.GBrain is tagged with agent skill, memory, context retrieval, state management capabilities.
OpenAgent capability taxonomy.- Dedicated docs link is missing.
- Repository freshness has not been recorded.
Next action
How to start evaluating GBrain
Inspect repository
Check license, recent activity, issues, examples, and security-sensitive code paths.
Open sourceClone the repository
Use the repository as the source of truth for setup and current usage.
git clone https://github.com/garrytan/gbrain.git Compare
Alternatives and nearby resources
Use related resources to compare category fit, license, deployment model, and first-workflow behavior.
FAQ
Common questions about GBrain
What should I check before using GBrain?
Evaluate GBrain by reading its official source, then running one workflow end to end. Check when the skill should be invoked, what inputs it expects, what evidence it collects, and how easy it is to edit or version.
Is GBrain open source?
GBrain is listed with MIT based on the official source links in this profile. Re-check the repository, model card, or docs before production use.
Who should evaluate GBrain?
GBrain is most worth evaluating for builders experimenting with persistent agent context.