streetai-memory 0.1.0

Continuously learning memory layer for LLM applications: signals, stacks, decay, two-tier retrieval.

Street AI

Continuously learning memory layer for LLM applications. Your AI's memory grows forever. Your token bill doesn't.

Street AI sits between your application and the LLM API. It stores conversation as signals organized into stacks, decays old data automatically, and retrieves only what's relevant on each turn — so you send a tiny prompt instead of the full conversation history.

Status

Alpha (0.1.0). API will change. Pin a version if you depend on it.

Install

pip install streetai-memory

The PyPI name is streetai-memory; the import path is streetai:

from streetai import Memory, MemoryRegistry, Config

First use downloads a ~25MB embedding model (all-MiniLM-L6-v2) into a local cache.

To install with provider adapters:

pip install "streetai-memory[anthropic]"  # Anthropic
pip install "streetai-memory[openai]"     # OpenAI (also DeepSeek, Together, Groq)
pip install "streetai-memory[gemini]"     # Google Gemini
pip install "streetai-memory[all]"        # all of the above

Quickstart

from streetai import MemoryRegistry

registry = MemoryRegistry("./memory.db")
mem = registry.get("user_123")

mem.add_message("Hi, I'm planning a trip to Japan.", role="user")
mem.add_message("Great! Which cities?", role="assistant")

prompt = mem.build_prompt("What did I say about Japan?")

# prompt.messages   -> list of {role, content} ready for any LLM API
# prompt.retrieved  -> signals that were pulled in (pass to post_process)
# prompt.inspector  -> debug info (stacks activated, scores, etc.)

# After your LLM responds:
# response_text = your_llm(messages=prompt.messages)
# mem.post_process(prompt.retrieved, response_text)
# mem.add_message("What did I say about Japan?", role="user")
# mem.add_message(response_text, role="assistant")

For a fully runnable version, see examples/quickstart.py.

Drop-in adapters

The adapters wrap a real provider client. You use the same SDK API you already know; memory is read and written transparently on every call.

Anthropic

from anthropic import Anthropic
from streetai.adapters.anthropic import with_memory

client = with_memory(Anthropic(), memory_id="user_123")

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system="You are helpful.",
    messages=[{"role": "user", "content": "What did I mention earlier?"}],
)
print(response.content[0].text)

Full example: examples/anthropic_chat.py.

OpenAI

from openai import OpenAI
from streetai.adapters.openai import with_memory

client = with_memory(OpenAI(), memory_id="user_123")

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "What did I mention earlier?"}],
)
print(response.choices[0].message.content)

Full example: examples/openai_chat.py.

DeepSeek (uses the OpenAI adapter)

DeepSeek is OpenAI-API-compatible. Use the OpenAI adapter with base_url:

import os
from openai import OpenAI
from streetai.adapters.openai import with_memory

deepseek = OpenAI(
    api_key=os.environ["DEEPSEEK_API_KEY"],
    base_url="https://api.deepseek.com/v1",
)
client = with_memory(deepseek, memory_id="user_123")

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "What did I mention earlier?"}],
)

The same pattern works for Together, Anyscale, Groq, and any other OpenAI-compatible endpoint. Full example: examples/deepseek_chat.py.

Google Gemini

from google import genai
from streetai.adapters.gemini import with_memory

client = with_memory(genai.Client(api_key="..."), memory_id="user_123")

response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents="What did I mention earlier?",
)
print(response.text)

Full example: examples/gemini_chat.py.

How it works

your message
     |
     v
[1] split into chunks (sentence-sized signals)
     |
     v
[2] embed each chunk to a 384-dim vector
     |
     v
[3] assign to a stack (cluster of related signals) by cosine similarity
     |
     v
[4] when a new query arrives:
       - find top-K most relevant stacks (FAISS)
       - within those stacks, surface signals that pass the activation threshold
       - drop signals whose effective weight has decayed below death
     |
     v
[5] build a small prompt:
       [retrieved context] + [last N messages verbatim] + [new query]
     |
     v
[6] after the LLM responds:
       - boost signals that matched the response (they helped)
       - demote signals that didn't (they were noise)
       - decay continues until the signal is used again

Signals refresh their age clock every time they're retrieved — frequently useful data stays sharp; unused data fades. No retraining, no manual pruning.

Compared to alternatives

	Plain chat history	RAG (vector DB)	Street AI
Prompt grows with conversation	Yes — linear	No (replaces history)	No (compresses history)
Recent context kept verbatim	Yes	No — replaced by retrieval	Yes — recency window
Time-aware (decay)	No	No	Yes — built in
Learns from outcomes	No	No	Yes — boost/demote
Self-organizing	N/A	Manual chunking	Yes — auto-stacks
Cross-provider	Yes	Sometimes	Yes

Configuration

Override defaults with Config:

from streetai import MemoryRegistry, Config

cfg = Config(
    recency_turns=5,          # last 5 messages verbatim (default 3)
    decay_rate=1.0/86400,     # 1-day half-life (default ~ 1 week)
    stack_threshold=0.65,     # tighter stack assignment (default 0.55)
    activation_threshold=0.1, # min score for a signal to surface (default 0.15)
)

registry = MemoryRegistry("./memory.db", config=cfg)

All tunables: see streetai/config.py.

Limitations (v0.1)

• Sync clients only. Async wrappers come later.
• Non-streaming only. stream=True raises NotImplementedError.
• English-tuned defaults. Chunking and thresholds may need tuning for other languages.
• fastembed is required. Pluggable encoders come in a future version.

Development

git clone https://github.com/Tem-Degu/streetai-memory.git
cd streetai-memory
pip install -e ".[dev]"
pytest

License

Apache 2.0