mem0ai / mem0
A universal memory layer providing multi-level retention for users, sessions, and autonomous agents. It utilizes hybrid retrieval and temporal reasoning to rank memories by relevant dates and states.
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.
#
project
stars
01
mem0ai / mem0
Universal memory layer for AI Agents
★ 57.1K
02
volcengine / OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of co
★ 24.9K
03
supermemoryai / supermemory
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
★ 22.8K
04
garrytan / gbrain
Garry's Opinionated OpenClaw/Hermes Agent Brain
★ 19.8K
05
vectorize-io / hindsight official
Hindsight: Agent Memory That Learns
★ 15.2K
06
campfirein / byterover-cli
ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)
★ 4.8K
07
plastic-labs / honcho official
Memory library for building stateful agents
★ 4.5K
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!
★ 745
10
stephenschoettler / hermes-lcm
Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message
★ 625
11
elkimek / honcho-self-hosted
Self-host Honcho memory layer for Hermes Agent — OpenRouter + Venice, no code changes
★ 271
12
yoloshii / ClawMem
On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.
★ 178
13
Signet-AI / signetai
Local-first identity, memory, and secrets for AI agents. Portable state across models and harnesses.
★ 176
14
plur-ai / plur
Shared memory for AI agents
★ 145
15
EfficientContext / ContextPilot
Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic
★ 112
16
yepyhun / Brainstack
Memory kernel stack for Hermes agent
★ 38
17
keepnotes-ai / keep
Reflective memory for agents
★ 35
18
yantrikos / yantrikdb-hermes-plugin
YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with canonicalization, contradiction tracking, recency ran
★ 30
19
amanning3390 / flowstate-qmd
FlowState QMD — Anticipatory Memory for AI Agents. Hermes 2026 Hackathon Entry.
★ 29
20
alias8818 / hermes-tool-slimmer
Reduce Hermes Agent tool-schema overhead with keyword selection and Tool Search support
★ 20
21
Ladybug-Memory / hermes-memory-plugin
Ladybug memory plugin for Hermes Agent
★ 16
22
MukundaKatta / hermes-agentmemory
Pull-model episodic memory plugin for Hermes Agent. Real deletes, audit trace, BYO Claude. MIT.
★ 6
breakdown
volcengine / OpenViking
An open-source context database that uses a filesystem-based directory paradigm and tiered L0/L1/L2 loading. This approach significantly reduces token usage while improving task-completion rates via recursive directory retrieval.
supermemoryai / supermemory
A high-performance memory engine featuring sub-300ms recall and byte-level deduplication for prompt-cache discounts. It automates user profile maintenance and includes native connectors for Notion, GitHub, and Google Drive.
garrytan / gbrain
An opinionated brain for Hermes Agent that synthesizes cited answers with explicit gap analysis of missing information. It features a self-wiring knowledge graph for complex entity traversal and MCP support for tools like Cursor and Claude Code.
vectorize-io / hindsight
A learning-focused memory system implementing retain, recall, and reflect workflows for long-term knowledge. It offers a simple LLM wrapper for automatic storage and supports enterprise backends like PostgreSQL and Oracle AI Database.
campfirein / byterover-cli
A memory provider that treats context as a git repository, allowing for branching, merging, and versioning of markdown context trees. It delivers sub-100ms retrieval across a 5-tier system and includes built-in tools for code execution.
plastic-labs / honcho
A stateful agent library that extracts reasoning-based conclusions rather than relying on simple vector matching. It maintains evolving representations of users and projects in prompt-ready formats compatible with OpenAI and Anthropic.
greyhaven-ai / autocontext
A recursive self-improving context harness that uses five specialized agent roles to generate structured playbooks. It enables persistent knowledge transfer through CLI-first skill exports for Hermes Agent.
AxDSan / mnemosyne
A zero-dependency, SQLite-backed memory system delivering sub-millisecond performance. It combines vector similarity, FTS5, and importance scoring in an MCP-ready integration.
stephenschoettler / hermes-lcm
A lossless context management plugin utilizing a hierarchical summary DAG for depth-aware compaction. It preserves raw messages in SQLite and provides dedicated tools like lcm_grep for precise retrieval.
elkimek / honcho-self-hosted
A self-hosted backend for Honcho that enables private, cross-session persistence for Hermes Agent. It supports local inference servers and any OpenAI-compatible LLM via a Docker-based setup.
yoloshii / ClawMem
A local-first context engine that operates without API keys or cloud dependencies. It employs a hybrid retrieval system combining BM25, vector search, and knowledge graphs.
Signet-AI / signetai
A portable identity and memory layer that ensures state continuity across Hermes Agent, Claude Code, and OpenClaw. It uses SQLite and markdown for local data ownership and hybrid graph-vector retrieval.
plur-ai / plur
A shared memory layer for multi-agent systems using an open YAML engram format. It implements ACT-R activation to strengthen relevant facts and decay stale information without API costs.
EfficientContext / ContextPilot
A context optimization tool that increases cache hits and reduces prefill latency through prefix reordering and deduplication. It is designed to accelerate inference across SGLang, vLLM, and the Hermes ecosystem.
yepyhun / Brainstack
A memory kernel stack that consolidates temporal continuity, graph truth, and corpus retrieval. It leverages SQLite, Kuzu, and Chroma to provide bounded evidence packing that reduces prompt noise.
keepnotes-ai / keep
A reflective memory system featuring semantic search and ranked graph traversal. It automatically indexes local directories and URLs, using edge tags to create navigable relationships with inverse links.
yantrikos / yantrikdb-hermes-plugin
An embedded, self-maintaining plugin that provides explainable recall via why_retrieved tags. It tracks contradictions and handles canonicalization without requiring a separate server or GPU.
amanning3390 / flowstate-qmd
An anticipatory memory system that prefetches context by monitoring agent session logs. It uses a local-first SQLite-vec storage and an MCP-native server for seamless integration with coding agents.
alias8818 / hermes-tool-slimmer
A utility that reduces prompt overhead by using BM25-based ranking to select only the most relevant tool schemas. It includes a dashboard to monitor token savings across hybrid and Anthropic Tool Search modes.
Ladybug-Memory / hermes-memory-plugin
A local-only plugin using a columnar .lbdb embedded graph database. It employs importance-weighted recall to surface high-priority memories and supports GLiNER2 for entity extraction.
MukundaKatta / hermes-agentmemory
A pull-model episodic memory plugin that ensures complete deletion of memories without leaving persistent summaries. It provides a trace.jsonl audit log to track every memory operation for transparency.