Mneme

Mneme is an open-source orchestration harness and memory governance framework developed by MnemeHQ designed to prevent architectural drift across the agentic AI software development lifecycle (SDLC). In day-to-day operations, Mneme acts as an enforcement layer and middleware for AI agents, integrating with orchestrators like LangChain to enforce repository-level architectural decisions and project memory. It tracks decisions and constraints using structured project memory records (such as `.mneme/project_memory.json`) and Architectural Decision Records (ADRs), validating modifications and agent outputs against defined project guidelines during local runs and pull request reviews. What differentiates Mneme from general-purpose coding agents is its strict focus on architectural drift prevention and memory provenance. Rather than acting purely as an interactive chat agent or code generator, Mneme enforces integrity rules—such as ADR source hash verification and PR isolation gates—ensuring that autonomous agent changes adhere to persistent repository rules and constraints. Mneme is hosted on GitHub under an open-source model. It is actively maintained with integrations for agent middleware, continuous memory tracking, and CI/CD gating workflows.

Tags: ai agent, cli, codebase, coding agent, developer tools, OpenSource

Visit Mneme

Key features

• Architectural Drift Prevention — Prevents autonomous agents from violating high-level repository constraints and architectural designs during automated changes. - Project Memory Reconciliation — Tracks decisions and system state in a structured .mneme/project_memory.json memory file linked directly to repository commits. - ADR-Backed Decision Governance — Enforces Architectural Decision Record (ADR) alignment with cryptographic SHA-256 source hash validation to prevent documentation desynchronization. - LangChain Middleware Integration — Connects directly into LangChain agent workflows to govern agent visibility, constraints, and tool invocation scopes. - PR Isolation & Merge Gating — Provides verification checks that prevent merges until memory definitions and codebase implementations reconcile accurately.

Use cases

Use Case: Architectural Drift Enforcement A development team running automated coding agents integrates Mneme to ensure changes made across multi-agent workflows adhere strictly to established design patterns and architectural boundaries.

Use Case: ADR Source Verification in CI/CD Engineers track architecture changes in markdown ADRs and use Mneme's hash validation to automatically block pull requests where code changes diverge from recorded architecture decisions.

Use Case: LangChain Agent Memory Governance A team building custom developer agents uses Mneme as middleware to bind LangChain actions to repository memory, ensuring the agent retrieves correct project rules and operates within assigned backend scopes.

Who it is for

Mneme is suited for software architects, platform engineers, and engineering teams orchestrating automated AI coding agents that need strict architectural governance and persistent project memory. It is less relevant for individual developers looking for a simple standalone conversational autocomplete or interactive chat tool.

Install guide

Installation Mneme can be installed or integrated via standard Python packaging or directly from GitHub: bash pip install mneme # Or clone the repository directly git clone https://github.com/MnemeHQ/mneme.git cd mneme

First Run Initialize repository memory and verify the project configuration: bash # Initialize the .mneme directory and project memory file mneme init # Validate ADR alignment and memory hash integrity mneme check

Example Session Run memory verification against your current branch before opening a pull request: bash # Verify that memory definitions match ADR hashes mneme reconcile --verify-hashes # Run agent middleware validation against project memory mneme agent check --scope backend

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

• Flameox — Flameox is an open-source coding agent harness and orchestration framework maintained by morluto. Built to support hybrid development workflows across…
• Grite — Grite is an open-source terminal coding agent harness developed by Neul Labs. Implemented in Rust, it provides a lightweight command-line…
• Amp — Amp (developed by AmpCode) is an autonomous coding agent platform and remote development harness designed to execute software engineering tasks…
• Kiro — Kiro is an agentic engineering platform and CLI coding agent built and operated by AWS. It extends beyond standard code-completion…
• Continue — Continue is an open-source AI code assistant and agent framework originally developed by the Continue team (continuedev) and recently acquired…
• SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…