Gives AI agents persistent memory across sessions, with semantic search, a knowledge graph, and document storage backed by SQLite. Load stored context at session start, recall past work, and save important information for later.
Claude Code
> /plugin marketplace add agentic-box/memora> /plugin install memora@memora
Codex
$ npx skills add agentic-box/memora -a codex
Cursor
$ npx skills add agentic-box/memora -a cursor
Gemini CLI
$ npx skills add agentic-box/memora -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add agentic-box/memora$ copilot plugin install memora@memora
OpenCode
$ npx skills add agentic-box/memora -a opencode
Windsurf
$ npx skills add agentic-box/memora -a windsurf
Give your AI agents persistent collective memory An MCP memory layer for agents: structured storage, semantic retrieval, graph relations, and source-backed cross-session context.
Absorb agent work into durable graph memory, then use memory_digest(topic) to retrieve relevant memories, TODOs/issues, related edges, and source IDs.
Features · Preview · Install · Usage · Config · Multi-DB · Containers · Live Graph · Cloud Graph · Chat · Semantic Search · Documents · LLM Dedup · Linking · Neovim
Core Storage
/mcp/<name> (see Multi-database routing)Absorb & Lineage
dry_run previewfollow modes: active, latest, full_history)
follow=latest/active hide every version, memory_get on one answers not_found with retired: true naming the delete ("retired by deleting #N"), follow=all still reads it, and adding a supersedes edge to a retired id does not restore it.memory_absorb never supersedes an item record (metadata.kind = "item-record" or tag item-record): the fact is written and linked related_to instead. Todos and issues are protected by the type boundary (a plain fact never supersedes a typed one).memory_digest(topic) bundles relevant memories, open TODOs/issues, related edges, and source IDs into one retrievalSearch & Intelligence
Document Storage
Tools & Visualization
/api/v1)The server can expose a plain JSON API at /api/v1/<store>/{health,search,absorb}
(the wire contract is contracts/memora-api/v1/). It is off unless
MEMORA_API_TOKENS_FILE is set to an absolute path; an unset variable is an
intentional state and is logged at INFO, not ERROR (issue 1131).
The file holds sha256 digests, never tokens. The server opens it
O_RDONLY | O_NOFOLLOW | O_CLOEXEC and requires a regular file, no group/other
permission bits and at most 4 KiB, owned by the server's user, under parents
that are not symlinks and not group/world-writable. On a read-only mount
(for example the deploy's read-only secrets mount, where rootful docker reads
the operator's file as root and statvfs reports ST_RDONLY), the owner match
for the file and for its read-only parents is not required; every other check
still applies. A failed reload keeps the last good token set.
scripts/mint_api_token.sh mints a token into a new 0600 file and adds its
digest to api-tokens.json; scripts/deploy-memora-all.sh sets
MEMORA_API_TOKENS_FILE when that file is in its secrets directory. Request
semantics (401/403/404) and rotation are in the contract.
Two paths. pip is a local stdio child the client spawns. A container is a detached HTTP service you start with up; with MEMORA_DATABASES it serves multiple stores from one process. The LaunchAgent supervises the proxy, not the container — after a host restart the listener can come back while its upstream is still stopped. If you are running memora as a service, the container path is the install.
pip install memora-mcp
The PyPI package is memora-mcp (bare memora on PyPI is an unrelated project). Includes cloud storage (S3/R2) and OpenAI embeddings out of the box.
# Optional: local embeddings (offline, ~2GB for PyTorch)
pip install "memora-mcp[local]"
# Latest development version straight from git
pip install "git+https://github.com/agentic-box/memora.git"
Then spawn it from .mcp.json with "command": "memora-server" (see Configuration).
Default runtime is Apple's container CLI. Every container operation scripts/memora-instance.sh performs (build, up, status, logs, down) uses $MEMORA_CONTAINER_BIN (default container). The generated proxy process does not; it hardcodes container list.
Before the first build:
Install Apple's container CLI (signed pkg from its GitHub releases). It needs a Mac with Apple silicon running macOS 26 — Apple does not support older macOS versions for container.
Start the runtime — Apple's documented first command, which also installs a kernel if none is configured:
container system start
Clone this repo and cd into it:
git clone https://github.com/agentic-box/memora.git
cd memora
Copy the instance template. It ships with INSTANCE=myinstance so the later build/up/proxy lines match without renaming. Edit PORT and a backend (STORAGE_URI, VOLUME, or MEMORA_DATABASES):
cp instances/example.env instances/myinstance.env
Create the credential file and install the proxy the LaunchAgent will run. cred_args() requires a .mcp.json whose mcpServers.memora.env holds CLOUDFLARE_API_TOKEN (D1 access) and the embedding/LLM keys — up dies if that file is missing. The script looks for ~/.config/memora/credentials.mcp.json unless the instance file sets CRED_SOURCE to another path; there is no other fallback. Separately, proxy renders a plist whose executable is $MEMORA_PROXY_BIN (default ~/.local/libexec/memora/memora_proxy.py) and whose logs live in $MEMORA_LOG_DIR (default ~/.local/var/log) — nothing creates either on a fresh clone.
mkdir -p ~/.config/memora ~/.local/libexec/memora ~/.local/var/log
cp scripts/memora_proxy.py ~/.local/libexec/memora/
# real values; any key is fine, an absent file is not
# the default umask is permissive -- chmod 600 keeps other local accounts out
cat > ~/.config/memora/credentials.mcp.json <<'JSON'
{"mcpServers":{"memora":{"env":{"CLOUDFLARE_API_TOKEN":"REPLACE","OPENAI_API_KEY":"REPLACE"}}}}
JSON
chmod 600 ~/.config/memora/credentials.mcp.json
That JSON is the minimal correct config: both the LLM and embeddings use the
default OpenAI host with a real OpenAI key. Do not add
OPENAI_BASE_URL pointing at OpenRouter without the embedding pair from
Embeddings — OpenRouter has no embeddings
endpoint, every embed call 404s, and memora silently falls back to TF-IDF
keyword bags while looking healthy.
Then:
./scripts/memora-instance.sh build myinstance # tags IMAGE from myinstance.env (memora-pilot if IMAGE is unset)
./scripts/memora-instance.sh up myinstance # runs that same IMAGE
./scripts/memora-instance.sh proxy myinstance # render the LaunchAgent; run the printed launchctl
up does not publish a host port. The listener the workspace connects to is the proxy. proxy only renders a macOS LaunchAgent and prints the launchctl commands — it does not load the service. Run those printed commands.
The printed workspace URL is always http://127.0.0.1:<PORT>/mcp (the registry default). For a non-default store, append /<name> yourself — a bare /mcp on a registry silently binds MEMORA_DEFAULT_DB:
{"mcpServers": {"memora": {"type": "http", "url": "http://127.0.0.1:<PORT>/mcp/<store>"}}}
Proxy rationale, credentials, instance files, and MEMORA_CONTAINER_BIN: Container Deployment.
Usage
The server runs automatically when configured in Claude Code. Manual invocation:
# Default (stdio mode for MCP)
memora-server
# With graph visualization server
memora-server --graph-port 8765
# HTTP transport (alternative to stdio)
memora-server --transport streamable-http --host 127.0.0.1 --port 8080
Configuration
Add to .mcp.json in your project root:
Local DB:
Stars on GitHub
Reads text from scanned pages, photos and PDFs and returns it as structured Markdown or JSON, so you can pull tables, formulas and headers out of a document without retyping them. Covers many languages and works as input for AI tools.
@paddlepaddleGives your AI assistant a memory that persists across sessions, so it remembers your preferences and earlier work in this repository instead of starting fresh. Search, forget, pause and resume memories with simple commands.
@mem0aiGives AI agents a library of ready-made skills for scientific work such as metabolic flux analysis, protein experiment design, time series modeling, and analytical method validation, so research tasks need less hand-built code. It works with any agent that supports the open Agent Skills standard.
@k-dense-aiGives Claude Code skills, agents, and commands for PostHog analytics, session replay, feature flags, error tracking, and LLM observability. Includes MCP server setup and project access checks.
@posthogInstall it with the command on its page. It includes memora. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it