by dev.agentreliability
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
https://agentreliability.dev/mcp?via=manifestok 4 d ago
Graph-structured knowledge.
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Solve it once. From then on, your AI knows. Experience for coding agents, hosted in the EU.
Model Context Protocol server for FalkorDB graph databases - enables AI assistants to query and manage graph data using natural language
Core of ai-agent-context: repository knowledge graph, architecture detection, incremental scanning, deterministic .agent/ serialization. Local-first, zero runtime dependencies, no LLM required.
Model Context Protocol adapter for ai-agent-context. Exposes the repository knowledge graph to MCP clients over stdio. Contains no business logic of its own.
Git-native context layer for AI coding agents: scan a repository into a structured, versionable .agent/ knowledge layer and query it (CLI + programmatic API).
The Runpod plugin's skills, reference docs, golden paths and concept graph as one JSON bundle, for programs such as the Runpod MCP server
A Model Context Protocol server for generating charts using AntV.
MCP server that indexes codebases into an AST knowledge graph with semantic search, call graph traversal, and HTTP route tracing
Code graph MCP: 81 languages, 88 frameworks, 72.7% fewer PR-review tokens, comprehension at parity
MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Self-hosted memory for LLMs in TriliumNext, structured by the server and editable by you.
Local-first agentic memory: the engram MCP server launcher. Memory + knowledge graph + beliefs + code intelligence for any MCP client.
Local-first MCP server: version-correct library docs, code map, and offline drift for your repo.
MCP server for Microsoft Graph Teams integration
Self-contained MCP server for Sepia — a personal knowledge-graph memory server. Talks to the Sepia REST API (SEPIA_URL + SEPIA_API_KEY); stdio or HTTP transport.
Local-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance.
Task management for AI-driven development, built for Claude Code: plan from a PRD, then work tasks one at a time with slash commands, a CLI or an MCP server.