Skip to main content
Glama
605,004 tools. Updated 2026-09-23 22:20

"Techniques for enabling agents to retain and utilize information across multiple sessions" matching MCP tools:

  • Generate raw test data values: random seeded rows across multiple fields, or boundary, random, and invalid values for a single typed field. Use for data inputs, not technique-based test cases.
    MIT
  • Export LoreConvo sessions to Anthropic managed-agents memory format for import into memory stores. Filters sessions by project, IDs, or days back.
    Business Source 1.1
  • Find common free time slots across multiple agents' calendars and authorized human calendars, returning available meeting times within a specified range.
    Apache 2.0
  • Search shared long-term memory across all agents and sessions to retrieve prior decisions, preferences, project facts, and past incidents before assuming or asking.
    -

Matching MCP Servers

  • F
    license
    Not graded
    quality
    C
    maintenance
    MCP server that silently monitors state changes in structured data sources (e.g., government open data) and provides a pull-based channel for AI agents to retrieve real mutations since their last cursor.
    -

Matching MCP Connectors

  • Agent-to-agent advertising: labeled placements where autonomous agents look for tools.

  • List a public API where AI agents discover tools, after a bounded readiness check.

  • Add multiple nodes to a knowledge graph by defining their name, type, and observations, with data persisted across sessions in ZeroDB cloud.
    MIT
  • List agents with a memory sidecar to identify which ones retain context across sessions. Helps you know which agents have persistent memory.
    MIT
  • Aggregate and synthesize investment research from multiple data sources to analyze market intelligence, competitive landscapes, and financial impacts.
    MIT
  • Manage compact project memory across chats, agents, and IDEs: record active work, complete and archive sessions, search history, and update durable rules.
    MIT
  • Add an authenticated session to the MCP by providing a magic link, JWT, or email token, enabling access to property shares across multiple MLS agents.
    MIT
    Destructive
  • Save work progress checkpoints to maintain continuity across sessions and agents. Records current steps, next actions, risks, outputs, and structured changes for seamless handoffs.
    AGPL 3.0
  • Write markdown entries to a shared blackboard for sharing contracts, decisions, status, and pointers across agents and sessions. Keys overwrite values; reference large files instead of embedding.
    MIT
  • Store confirmed facts in shared memory for AI agents to retain knowledge across sessions, using entity/key/value triples with conflict detection.
    AGPL 3.0
  • Search cached session and activity data for quick retrieval. Use to filter by type or state across multiple sessions without fresh synchronization.
    MIT
  • Create a persistent browser session to maintain authentication state across multiple Pagebolt operations, enabling AI workflows to log in once and perform authenticated actions.
    MIT
  • Store new memories to retain novel insights, decisions, and debugging solutions across sessions. Automatically rejects near-duplicates to avoid clutter.
    Apache 2.0
  • Run all seven typosquatting detection techniques on a domain, deduplicate variants, and optionally resolve to report only registered domains.
    MIT
  • Save or update session state to resume work across MCP sessions. Merges new progress, cursor, and working set with existing state, enabling agents to continue tasks without losing context.
    MIT