DSPM Memory

Compress multi-turn LLM conversations by 80%+ while guaranteeing every constraint and decision survives.

The Problem

Long conversations eat your context window. Naive truncation drops the constraint from turn 3 that the entire system depends on. DSPM fixes this.

How It Works

DSPM converts each conversation turn into typed semantic patches — constraint, decision, code, entity, structure — and compresses them under a fixed token budget. Critical patches (constraints and decisions) are structurally protected: they survive compression even when everything else is trimmed.

Raw conversation (452 tokens, 18 turns)
        ↓
Semantic extraction → 28 patches, 18 critical
        ↓
7-stage compression pipeline
        ↓
Compressed context (249 tokens) — 100% of criticals intact

The 7-stage pipeline: dedup → slot fusion → delta encoding → causal pruning → utility scoring → shadow selection → adaptive budgeting.

Install

pip install dspm-memory

Requires Python 3.9+. Works with any OpenAI-compatible LLM provider.

Quickstart

from openai import OpenAI
from dspm import DSPMMemory

# Works with OpenAI, Groq, Together, Ollama, or any OpenAI-compatible endpoint
llm = OpenAI(
    api_key="sk-...",
    # base_url="https://api.groq.com/openai/v1"  # uncomment for Groq
)

memory = DSPMMemory(budget=250, llm_client=llm, model="gpt-4o-mini")

memory.add_turn("user", "Build a REST API. Must use PostgreSQL, JWT auth, deadline is Friday.")
memory.add_turn("assistant", "PostgreSQL with SQLAlchemy, JWT via python-jose. Access tokens 15 min.")
memory.add_turn("user", "All PII must be encrypted at rest with AES-256. No exceptions.")
memory.add_turn("assistant", "AES-256 at rest for all PII fields, keys in AWS KMS with quarterly rotation.")

context = memory.get_context(query="What are the hard requirements?")
print(context)
print(memory.stats)

Output:

[CON] Stack: PostgreSQL, JWT auth. Deadline Friday.
[CON] Access tokens 15 minutes.
[CON] All PII must be encrypted at rest with AES-256. No exceptions.
[CON] AES-256 at rest; keys in AWS KMS, quarterly rotation.

Every constraint is present. Every time.

Persistence: Memory Across Chats and Sessions

Save the notebook when a chat ends, load it when the next one starts — Chat 2 remembers Chat 1, and revisions supersede old values across sessions:

# Chat 1 — Monday
memory = DSPMMemory(budget=250, llm_client=llm, model="gpt-4o-mini")
memory.add_turn("user", "Building a budgeting app. Hard rules: must work offline, deadline Oct 20.")
# ... chat ...
memory.save("user_dhruv.json")

# Chat 2 — Thursday, new process, fresh start
memory = DSPMMemory(budget=250, llm_client=llm, model="gpt-4o-mini")
memory.load("user_dhruv.json")
memory.get_context(query="What were my hard rules?")
# → [CON] must work offline
# → [CON] deadline Oct 20        ← recalled from Chat 1, zero API cost

# Revisions work across chats too:
memory.add_turn("user", "The deadline moved to November 5.")
# → Oct 20 is superseded. November 5 replaces it.

Save files are portable JSON, written atomically (a crash mid-save can't corrupt the notebook), and merge-on-load means saved revisions supersede stale values. One file per user = each person's long-term memory.

The Guarantee

[CON] and [DEC] patches are structurally protected:

• Never dropped by deduplication, fusion, or pruning
• Under budget pressure, payloads are trimmed numbers-first — thresholds, versions, and units survive longest
• When a constraint is revised mid-conversation (e.g. TTL 60s → 300s), the new value supersedes the old
• A critical is only dropped as a last resort: every critical already at its 2-word floor and budget still cannot hold them

Ablation result: Removing the shadow-selection mechanism collapses CRR from 100% to 37.9%, isolating the guarantee to a single identifiable component.

Results

Tested across 7 domains × 40 turns each:

CRR = Critical Retention Rate. TRR = Token Reduction Ratio.

Supported Providers

# OpenAI
llm = OpenAI(api_key="sk-...")

# Groq (free tier available)
llm = OpenAI(base_url="https://api.groq.com/openai/v1", api_key="gsk-...")

# Together AI
llm = OpenAI(base_url="https://api.together.xyz/v1", api_key="...")

# Ollama (local, no key needed)
llm = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")

API Reference

DSPMMemory(budget, llm_client, model)

The budget can be changed at any time:

memory.budget = 100        # takes effect on the next get_context() call
memory.set_budget(100)     # explicit alternative — same effect

Methods

Properties

Paper

DSPM: A Critical-Retention Approach to Long-Context Memory Compression for LLM Conversations
Dhruv Dubey, 2026
Zenodo: 10.5281/zenodo.19438636

Version History

License

MIT © 2026 Dhruv Dubey