mem0ai / mem0
The official Hermes Agent memory provider offering a universal memory layer for user, session, and agent state. It supports hybrid retrieval via semantic, keyword, and entity matching across managed cloud or self-hosted deployments.
Best Memory Providers for Hermes Agent
The top community-built memory and context management tools for Hermes Agent, ranked by GitHub stars. Memory is what makes Hermes self-improving — these tools extend its built-in recall with long-term semantic memory, graph-based retrieval, and cross-session persistence.
For the architecture behind these tools, read The Hermes Agent Memory Guidebook.
#
project
stars
01
mem0ai / mem0
Universal memory layer for AI Agents
★ 58.5K
02
supermemoryai / supermemory
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
★ 27.0K
03
volcengine / OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of co
★ 25.6K
04
garrytan / gbrain
Garry's Opinionated OpenClaw/Hermes Agent Brain
★ 22.7K
05
vectorize-io / hindsight official
Hindsight: Agent Memory That Learns
★ 16.3K
06
plastic-labs / honcho official
Memory library for building stateful agents
★ 5.1K
07
campfirein / byterover-cli
ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)
★ 4.9K
08
greyhaven-ai / autocontext
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
★ 1.2K
09
AxDSan / mnemosyne
The Zero-Dependency, Sub-Millisecond AI Memory System for Hermes Agents and Everyone Else!
★ 1.1K
10
stephenschoettler / hermes-lcm
Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message
★ 716
11
elkimek / honcho-self-hosted
Self-host Honcho memory layer for Hermes Agent — OpenRouter + Venice, no code changes
★ 302
12
Signet-AI / signetai
Local-first identity, memory, and secrets for AI agents. Portable state across models and harnesses.
★ 194
13
plur-ai / plur
Shared memory for AI agents
★ 186
14
yoloshii / ClawMem
On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.
★ 182
15
EfficientContext / ContextPilot
Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic
★ 115
16
yantrikos / yantrikdb-hermes-plugin
YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with canonicalization, contradiction tracking, recency ran
★ 58
17
yepyhun / Brainstack
Memory kernel stack for Hermes agent
★ 42
18
keepnotes-ai / keep
Reflective memory for agents
★ 36
19
amanning3390 / flowstate-qmd
FlowState QMD — Anticipatory Memory for AI Agents. Hermes 2026 Hackathon Entry.
★ 33
20
alias8818 / hermes-tool-slimmer
Reduce Hermes Agent tool-schema overhead with keyword selection and Tool Search support
★ 23
21
Ladybug-Memory / hermes-memory-plugin
Ladybug memory plugin for Hermes Agent
★ 17
22
MukundaKatta / hermes-agentmemory
Pull-model episodic memory plugin for Hermes Agent. Real deletes, audit trace, BYO Claude. MIT.
★ 6
23
futurebrowser / hermes-exabase-plugin
Exabase memory plugin for Hermes Agent.
★ 4
breakdown
supermemoryai / supermemory
An official Hermes Agent memory provider featuring a custom vector graph engine and byte-level deduplication for high-efficiency recall. It automates fact extraction and integrates with external connectors like Google Drive, Notion, and GitHub.
volcengine / OpenViking
An official Hermes Agent memory provider that uses a tiered L0/L1/L2 loading system to significantly reduce token consumption. It organizes memories via a filesystem-based structure and provides visualized retrieval trajectories for debugging.
garrytan / gbrain
An opinionated brain for Hermes Agent that synthesizes cited answers and performs explicit gap analysis on missing information. It utilizes a self-wiring knowledge graph to handle complex entity relationship queries and scoped multi-user access.
vectorize-io / hindsight
A learning-focused memory system that implements retain, recall, and reflect workflows for long-term agent growth. It acts as an LLM wrapper that automates storage and retrieval across providers like OpenAI, Anthropic, and Ollama.
plastic-labs / honcho
A reasoning-first memory library that extracts conclusions from conversations to build stateful agents. It employs peer-centric modeling and a hybrid search combining BM25 and vector retrieval.
campfirein / byterover-cli
An official Hermes Agent memory provider that treats context as a git repository, enabling versioning via commits, branches, and merges. It features a 5-tier retrieval system for sub-100ms latency and supports cloud sync for team knowledge sharing.
greyhaven-ai / autocontext
A recursive self-improving context harness that uses real-world evaluation and feedback loops to optimize agent performance. It generates persistent playbooks and structured execution traces across various providers including Claude Code and MCP.
AxDSan / mnemosyne
A zero-dependency memory system providing sub-millisecond retrieval latency using SQLite storage. It features a temporal knowledge graph and episodic memory compression with native MCP support for AI clients.
stephenschoettler / hermes-lcm
A lossless context management plugin that uses a hierarchical DAG to compact conversation history without losing detail. It provides specialized tools for grepping and expanding summaries stored in a local SQLite database.
elkimek / honcho-self-hosted
A self-hosted backend for the Honcho library that enables private cross-session persistence for Hermes Agent. It supports any OpenAI-compatible LLM and includes automated Docker, PostgreSQL, and Redis setup scripts.
Signet-AI / signetai
A local-first identity and secrets layer that provides portable state across Hermes Agent and other MCP clients. It features a repairable memory system allowing users to edit, delete, or reclassify agent context via SQLite.
plur-ai / plur
A shared memory layer for multi-agent systems using an open YAML engram format to eliminate API costs. It utilizes ACT-R activation to strengthen relevant facts while decaying stale information over time.
yoloshii / ClawMem
An on-device context engine that operates entirely locally without cloud dependencies or API keys. It combines BM25, vector search, and knowledge graphs via MCP server and Claude Code hooks.
EfficientContext / ContextPilot
A context optimization tool that increases prefill speed by 1.5–3× through prefix cache reuse. It reduces prompt token usage by approximately 36% and provides native plugin support for Hermes Agent.
yantrikos / yantrikdb-hermes-plugin
An embedded, self-maintaining memory plugin that provides explainable recall via 'why_retrieved' tags. It includes first-class contradiction tracking and canonicalization without requiring a separate server or GPU.
yepyhun / Brainstack
A memory kernel stack that consolidates temporal continuity, graph truth, and corpus retrieval. It leverages a multi-layered storage approach using SQLite, Kuzu, and Chroma to provide bounded evidence packing.
keepnotes-ai / keep
A reflective memory system combining semantic search with ranked graph traversal. It automatically indexes local directories, URLs, and multimedia files using edge tags to create navigable relationships.
amanning3390 / flowstate-qmd
An anticipatory memory system that prefetches context by monitoring agent session logs. It uses local-first storage with SQLite-vec and GGUF models via an MCP-native server.
alias8818 / hermes-tool-slimmer
A utility that reduces prompt token overhead by using local BM25 ranking to select only relevant tool schemas. It includes a dashboard to track token savings and is compatible with Hermes Agent v0.14.0.
Ladybug-Memory / hermes-memory-plugin
A local-only plugin using an embedded .lbdb graph database with importance-weighted recall to surface high-priority memories. It supports BM25 keyword search and optional GLiNER2 entity extraction.
MukundaKatta / hermes-agentmemory
A pull-model episodic memory plugin that ensures complete deletion of events to prevent persistent summaries from haunting future recall. It provides a trace.jsonl audit log for every memory operation.
futurebrowser / hermes-exabase-plugin
A plugin that integrates Exabase M-1 for self-organizing long-term agent memory. It provides tools for manual storage and searching, featuring configurable query expansion and result reranking.