LangGraph is a library for building stateful, multi-actor applications with LLMs. It extends LangChain with a flexible graph system to coordinate agent workflows.
Agent memory for facts that change. When a user corrects something, Recall replaces the old fact, tells the agent what it replaced, and keeps the old value in a history. Ask what was believed on any date, see every change to a fact, or diff two dates. Runs locally on polign_db, Postgres with pgvector, MongoDB, or Qdrant. Apache 2.0.
14
5
6
Apache 2.0
Why this server?
Offers a LangGraph checkpoint saver that persists agent state and memories with AES-256-GCM encrypted storage via the synapse-layer-langgraph integration.
MCP-native persistent memory for AI agents. Stores and retrieves encrypted memories with Trust Quotient scoring, cross-agent handover protocol, and immutable audit trail. 13 tools. Remote endpoint available.
13
52 PyPI
13
Apache 2.0
Why this server?
Provides an adapter that drops into LangGraph agent execution nodes to guard tool dispatches before they run, raising a CircuitBreakerException when a tool call (e.g. a bash command with shell injection) is halted by AST containment rules.
Enables Claude Code to query and control the SuperInstance fleet, including fleet status, conservation law checks, semantic search, and agent registry.
8
347 npm
MIT
Why this server?
Allows LangGraph agents to interact with KumoRFM for executing predictive queries, evaluating models, and managing graph metadata.
Enables AI assistants to query KumoRFM for predictive analytics on relational data, including graph management, natural language to PQL conversion, and training-free predictions.
12
25 PyPI
34
MIT
Why this server?
Provides a drop-in CCSStore adapter for LangGraph that adds read-side coherence and stale-write prevention via MESI protocol.
Coherence guard for shared files: when two agents write the same file, the stale writer is denied instead of silently overwriting, then reacquires and retries. Single-host, TLA+-verified.
10
248 PyPI
12
Apache 2.0
Why this server?
Provides a callback handler integration to trace LangGraph workflows for observability.
MCP-native LLM observability. Query your Spanlens traces, stats, cost anomalies, and savings from Cursor, Claude Desktop, or any MCP client. Open source (MIT).
7
13
MIT
Why this server?
Enables LangGraph agents to submit review requests and receive human decisions via the Gatewerk Python SDK.
Enables AI agents to discover and retrieve options market-structure data (GEX, gamma flip levels, dealer positioning, skew, max pain, expected-move levels, options flow, and ranked trade setups) from Trading Volatility's public API via natural language.
