wontopos 2.2.5

Wontopos — long-term memory for AI agents. Pure semantic retrieval, identical recall in every language, ~100× lower LLM bill.

Wontopos — long-term memory for AI agents

pip install wontopos

from wontopos import Client

mem = Client(api_key="wos-...")
mem.add("she prefers tea over coffee", user_id="alice")

# one call → short-term + long-term + context, ready for your LLM prompt
ctx = mem.recall("what does alice drink?", user_id="alice")

Why

• Pure semantic retrieval — no keyword/BM25. Identical recall in every language (한국어 · 日本語 · 中文 · English).
• No LLM in the loop — store / search / recall never call a language model. You pay embeddings, not generation.
• Bounded retrieval — recall() returns a small, fixed-size slice (~1,200 tokens) regardless of how much you've stored. Your LLM bill stops growing with history.

Methods

Method	Purpose
add(content, user_id, **metadata)	Store one memory
add_turn(user_msg, assistant_msg, user_id?)	Store a conversation exchange
add_bulk(content, user_id, category=, timestamp=)	Backfill a long history
update(old_memory_id, new_content, user_id?)	Supersede an old fact
search(query, user_id, limit=10, **opts)	Semantic search
recall(query, user_id)	One-call context (short + long + surrounding)
history(user_id)	Recent turns (short-term)
stats(user_id)	Counts
delete(user_id, memory_id)	Delete one memory
delete_all(user_id)	GDPR erase (delete every memory for the user)

All methods take a user_id — memories are isolated per user, then per account (your API key).

Who said it (speakers)

Every memory can carry a speaker: "me" for the assistant's own words, or a person's name for the people around your user. Search accepts a speaker too, so you can recall one person's words only.

mem.add("I promised to send the report on Friday", user_id="alice", speaker="me")
mem.add("Bob said the deadline moved to Tuesday", user_id="alice", speaker="Bob")
mem.search("what did Bob say about deadlines?", user_id="alice", speaker="Bob")

A store remembers up to 50 people to start (a limit we plan to raise); "me" never counts against it.

Recall caching

Opt in per search and repeated or extended queries reuse the previous result at 10% of the normal rate (Tablet and Scroll models):

hits = mem.search("...the conversation so far...", user_id="alice",
                  cache_control={"ttl": "5m"})   # or "1h"

Errors

Any non-2xx response raises WosError(status, message):

from wontopos import Client, WosError

try:
    mem.search("...", user_id="alice")
except WosError as e:
    if e.status == 401:
        print("API key invalid or revoked")
    elif e.status == 429:
        print("Rate limited — back off")
    else:
        print(e.status, e.message)

Self-host

Point at your own engine:

mem = Client(api_key="...", base_url="https://wos.your-host.com")

Links

• Homepage: https://wontopos.com
• API reference: https://wontopos.com/why (Developers tab)
• Repo: https://github.com/Irina1920/Wos_API

License: MIT.