Session memory for coding agents: local-first recall, drift detection, on-device inference.
Showing 97–144 of 2,642
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Agent-native TypeScript framework for building MCP servers.
OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.
Zettelkasten-based agent memory system with bidirectional links
Aggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime.
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
LLM-maintained personal wiki: cross-references sources, flags contradictions. Local markdown.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Agent Workflow Engine — multi-step MCP workflows with per-step directives and validation.
Git-backed platform for skills, tools, and context for AI agents
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
MCP server for the Rise of Machine AI tools directory.
Mem0-compatible persistent memory for AI agents: write facts once, recall them semantically.
Langfuse MCP server for accessing and analyzing telemetry data via natural language
Cloud-powered AI platform with multi-agent swarms, sandboxes, and workflow automation
Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine
Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
Persistent memory + git snapshots for Claude Code. Never lose context or code.
Universal memory runtime for AI agents — episodic, semantic, and procedural memory.
MCP server for delegating tasks to specialized AI sub-agents across coding tools
Persistent memory + FTS5 search MCP server for Claude Code conversation history.
Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.
Unified MCP & Skill management gateway, shared across AI agents, 99% context token savings
Knowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction.
Lossless archive and search for AI agent sessions across clients, exposed to agents over MCP.
Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.
Open-source AI agent control plane and software factory: govern every tool and model call.
Shared, verifiable memory for machines and AI. Encode where data lives; decode with any AI.
Query and manage Copilot Money personal finances — local reads, opt-in GraphQL writes.
Find and fix reliability and safety gaps in agent code, across nine agent SDKs.
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Memory, reflection and safety for AI agents. Hosted or local, no vector database.
Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.
Share agent skills across your team, scan them for risk, and track what's actually used.
Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis.
Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
Time MCP Server, giving LLMs time awareness capabilities.
Persistent memory MCP server for Claude Code, Codex and OpenCode, stored locally in SQLite
Cuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.
Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
Git-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes.
Manage your Uptime Kuma 2 instance from an LLM: monitors, status pages, notifications, maintenance
Graph-vector memory for AI assistants using FalkorDB and Qdrant
Extended reasoning with structured processes, persistence, and workflow guidance
