What is Greplica?
Greplica is an open-source tool that gives your engineering team and every coding agent a shared, persistent memory of the codebase. It continuously extracts decisions, constraints, gotchas, failed approaches, and file-level context from coding sessions, then retrieves only what matters for the task at hand. Unlike static docs or siloed agent memory, Greplica stays grounded in the repo, keeps knowledge fresh, and works across developers, agents, clones, and forks. It runs locally with no telemetry or offers a managed shared mode for team collaboration.
Who it's for
- Individual developers who want their coding agent to stop re-learning context every session and start remembering past decisions and constraints.
- Engineering teams that need a shared, up-to-date memory across multiple contributors, clones, and forks without relying on outdated documentation.
- AI agent users who want their coding agents to query persistent context before exploring the codebase, saving tokens and time on complex tasks.
Key features
Persistent, searchable engineering memory
Greplica explores your repo structure, code, and session transcripts to give your agent a maintained memory it can query before exploring. This eliminates the need for agents to spend minutes grepping around for context on every complex task.
Local and managed modes
Local mode stays fully local with no telemetry, keeping all data on your machine. Managed mode connects an authorized repository to shared team memory, allowing contributors on different clones and forks to query the same repository memory.
Agent quick start
Most users can install Greplica by pasting a single prompt into their coding agent from inside the repo. The prompt runs a short setup questionnaire, installs Greplica in local or managed mode, and either creates the first local context or connects to existing shared memory.
Shared managed memory with role-based access
Managed mode supports organization admins, members, contributors, and guests with different access levels. Contributors write proposals to their own persistent personal working scope, while memory_admins manage repository memory access. Invite links allow easy onboarding for multiple GitHub users.
What stands out
Greplica gives your coding agent a persistent, maintained memory it can query before exploring — no more re-learning context every session.
This is the core differentiator. While other tools rely on static documentation or siloed agent memory, Greplica continuously extracts and maintains context from actual coding sessions. It retrieves only what matters for the task at hand, keeping knowledge fresh and grounded in the repo. The ability to work across developers, agents, clones, and forks makes it uniquely suited for team environments where context sharing is critical.
Worth checking out if…
You're tired of your coding agent wasting tokens and time re-building context on work it already did, or if your team struggles with knowledge silos across different forks and clones. Greplica is especially valuable for teams using AI coding agents on complex codebases where decisions, constraints, and failed approaches need to be remembered and shared.
