Persistent repository memory
Explores repository structure, code, and session transcripts so the agent can query maintained memory before re-grepping the project.
Greplica
Greplica is a persistent, searchable engineering memory for AI coding agents. It helps agents recover repository context, query prior work, and share memory across local or managed repository workflows.
Persistent engineering memory for coding agents
Greplica is a persistent, searchable engineering memory for AI coding agents. It is designed to reduce the time agents spend re-learning repository context by exploring the codebase, repository structure, and prior session transcripts, then making that information queryable before the agent starts grepping again.
The project supports two operating modes. Local mode keeps data fully local with no telemetry, while managed mode connects an authorized repository to shared team memory so contributors on different clones and forks can query the same repository memory. The source also notes that Greplica requires Node.js 22-26 and can be installed through an agent-driven setup flow rather than by hand.
Core capabilities
Local and managed operation modes
Supports local mode for fully local operation and managed mode for shared repository memory across contributors.
Searchable context retrieval
Lets agents ask for repository context before acting, including example queries such as what to know before changing a subsystem.
Graph-based memory inspection
Provides a browser graph view to inspect current memory and generated relationships visually.
GitHub-based access control
Uses GitHub authentication and repository invitations to connect users to managed memory and shared access.
Managed memory reconciliation
Includes a managed reconciliation workflow that checks exact default-branch code and produces evidence-bound audits for memory updates.
Practical workflows
Context recovery before implementation
Use Greplica when an agent is starting a complex task and needs to recover repository facts, prior decisions, or subsystem context before making changes.
Shared team memory across clones and forks
Use managed mode when several contributors are working from separate clones or forks but need the same shared repository memory for coordinated work.
Visual review of stored memory
Use the graph view to inspect the current memory graph in a browser and understand how code, sessions, and related context are connected.
Memory reconciliation for managed repositories
Use the reconciliation workflow in managed repositories to compare memory updates against exact default-branch code and produce evidence-backed audits.
Pros and Cons
Pros
- Builds persistent memory from repository structure, code, and session transcripts instead of relying on each new session to rediscover context.
- Supports fully local operation with no telemetry in local mode.
- Enables shared team memory in managed mode for contributors working from different clones or forks.
- Provides queryable context and graph views to inspect stored memory before making changes.
- Documents a managed workflow for reconciling memory against exact default-branch code.
Cons
- The documentation is partial in the available source, so some setup and workflow details are not fully specified here.
- Managed mode depends on access to a managed Greplica server and administrator-granted repository or organization access.
- The source does not provide pricing for Greplica itself.
FAQ
How do you install Greplica?
Greplica is installed into a repository and can be used in local mode or managed mode. The source says most users should start by pasting the install prompt into their coding agent from inside the repo they want Greplica to remember.
Does Greplica run locally or require a hosted service?
Local mode stays fully local and uses SQLite for repository binding, role cache, hook policy, and runtime session metadata. The source says it has no telemetry in local mode.
What is managed mode used for?
Managed mode lets contributors on different clones and forks query the same repository memory. It requires Greplica 0.2.0 or later, access to a managed Greplica server, and a GitHub user who has been invited by an administrator.
What are the setup requirements?
The README says Greplica requires Node.js 22-26. The package metadata lists Node 22.x through under 27.x as the supported engine range.
Which agents or platforms does Greplica support?
The source mentions a browser graph view command, query examples for repository context, and managed-memory invite links, but it does not provide a complete list of supported agent platforms beyond examples that include Codex.
Quick Facts
- Category
- Developer Tool
- Source domain
- github.com
- Primary users
- AI coding agents and developers using them
- Deployment modes
- Local, managed
- Runtime requirement
- Node.js 22-26
- License
- MIT
Alternative a Greplica
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Ghost
Ghost è un assistente AI da terminale per chattare, generare codice ed eseguire task da riga di comando. Include modelli gratuiti, supporta Linux, macOS e Windows, ed è open source.
Goldfish
Goldfish is an AI memory app for macOS that helps you reply, write, summarize, and continue using the context already on your Mac. It stores memory locally and writes in your tone.
Lasso
Lasso is an ecommerce product data platform for enriching catalog records, processing supplier files, generating product content, and monitoring competitors. It combines a web app with a REST API, SDK, and MCP server for teams and developers.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
Struere
Struere is an AI-native platform for turning spreadsheet data into structured operational software with dashboards, alerts, and automations. It is aimed at teams that want to replace manual spreadsheet workflows without building custom tools from scratch.