Beads
A drop-in persistent memory upgrade for coding agents, exposed via an MCP integration.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Beads, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Beads gives coding agents durable, structured memory across sessions through a git-backed issue/memory store surfaced over MCP. Agents read and write memory beads to retain context between runs. Because it persists agent-authored content that later re-enters the context window, poisoned memory entries can influence future agent behavior.
Key features and capabilities
- Persistent cross-session agent memory
- Git-backed storage
- Drop-in integration
- Structured memory records
Use cases
- Long-running agent context retention
- Multi-session coding tasks
- Agent knowledge accumulation