recollect 0.8.1

Human-like memory for AI applications

recollect

Persistent memory SDK for LLM agents. See the project README for architecture and scoring details.

Install

pip install recollect    # or: uv add recollect

Quick Start

import asyncio
from recollect import CognitiveMemory

async def main():
    memory = CognitiveMemory()
    await memory.connect()

    await memory.experience(
        "The team decided to migrate from Redis to PostgreSQL for persistence."
    )

    thoughts = await memory.think_about("database decisions", token_budget=500)
    for thought in thoughts:
        print(f"[{thought.activation:.2f}] {thought.content}")

    await memory.close()

asyncio.run(main())

API

Method	Description
connect(db_url=None)	Connect to PostgreSQL. Uses DATABASE_URL env var if no argument.
experience(content)	Store a memory trace. LLM extracts entities, concepts, significance.
think_about(query, token_budget)	Retrieve memories that fit within a token limit. Returns list[Thought].
consolidate(threshold=None)	Merge and prune weak traces.
forget(trace_id)	Remove a trace.
reinforce(trace_id, factor=1.1)	Strengthen a trace.
facts(subject=None)	List persona facts.
start_session(user_id)	Begin a scoped session.
close()	Disconnect and release resources.

Environment Variables

Variable	Required	Default	Description
DATABASE_URL	Yes	postgresql://localhost:5432/memory_sdk	PostgreSQL connection string.
PYDANTIC_AI_MODEL	No	--	pydantic-ai model string in provider:model format (e.g., ollama:ministral-3, anthropic:claude-haiku-4-5-20251001).
ANTHROPIC_API_KEY	For Anthropic models	--	Anthropic API key. Read by pydantic-ai's Anthropic backend.
OPENAI_API_KEY	For OpenAI models	--	OpenAI API key. Read by pydantic-ai's OpenAI backend.
OLLAMA_BASE_URL	No	http://localhost:11434/v1	Ollama API endpoint.
MEMORY_EXTRACTION_MAX_TOKENS	No	8192	Max tokens for LLM extraction. Reasoning models consume thinking tokens before output; 8192 covers most cases.
MEMORY_CONFIG	No	--	Path to custom TOML config file.
MEMORY_EXTRACTION_INSTRUCTIONS	No	--	Override extraction prompt instructions (inline string).
MEMORY_EXTRACTION_TEMPLATE_PATH	No	--	Path to override extraction prompt (markdown with version / applies-to / placeholders header schema).
MEMORY_RECALL_TOKENS_ENABLED	No	true	Enable write-time token stamping and query-time activation.
MEMORY_RECALL_TOKENS_TOP_K	No	5	Max related traces to consider for token assessment.
MEMORY_RECALL_TOKENS_THRESHOLD	No	0.42	Min cosine similarity to consider a trace as related at write time.
MEMORY_RECALL_TOKENS_STRENGTH_THRESHOLD	No	0.1	Min token strength to activate at query time.
MEMORY_RECALL_TOKENS_REINFORCE_BOOST	No	0.1	Strength increment on token activation (capped at 1.0).
MEMORY_RECALL_TOKENS_DECAY_FACTOR	No	0.9	Multiply inactive token strength by this during consolidation.
MEMORY_RECALL_TOKENS_HOP_DECAY	No	0.85	Signal attenuation per token hop during query-time propagation.
MEMORY_RECALL_TOKENS_PROPAGATION_BLEND	No	0.5	Weight of propagated signal in the additive blend.
MEMORY_RECALL_TOKENS_MAX_ROUNDS	No	3	Max re-seeding iterations at query time.
MEMORY_RECALL_TOKENS_STABILITY_THRESHOLD	No	0.95	Top-K overlap fraction to stop re-seeding early.
MEMORY_RECALL_TOKENS_TOP_SEEDS	No	3	Token-discovered traces used as seeds per re-seeding round.
MEMORY_RECALL_TOKENS_SYSTEM_PROMPT	No	--	Override situational-assessment system prompt (inline string).
MEMORY_RECALL_TOKENS_USER_PROMPT	No	--	Override situational-assessment user prompt (inline string).

Configuration

[memory]
decay_rate = 0.05

[retrieval]
max_retrievals = 10

[extraction]
pydantic_ai_model = "ollama:ministral-3"   # pydantic-ai provider:model format

Config sections

Section	Controls	Key parameters
[database]	PostgreSQL connection	url
[memory]	Core memory model	initial_strength, consolidation_threshold, decay_rate
[working_memory]	Working memory capacity	capacity (default 7, range 5-9)
[retrieval]	Retrieval pipeline tuning	max_retrievals, search_limit, selection_threshold
[extraction]	LLM extraction	max_tokens, max_concepts, max_relations, pydantic_ai_model, template_path, embed_relation_tags
[extraction.model_settings]	Provider-specific settings forwarded to pydantic-ai	openrouter_reasoning, anthropic_thinking_budget, thinking, top_p
[embedding]	Local embedding model	model, dimensions
[persona]	Persona fact management	auto_extract, confidence_threshold
[recall_tokens]	Situational grouping at write + propagation at read	enabled, assessment_max_tokens, assessment_template_path, plus strength / decay / propagation knobs (env-var-exposed above)
[session]	Session summaries	summary_strength, summary_max_tokens

Full defaults: config.toml

from recollect.config import MemoryConfig

config = MemoryConfig(config_path=Path("./my-config.toml"))
memory = CognitiveMemory(config=config)

LLM Provider

from recollect.llm.pydantic_ai import PydanticAIProvider

# Model configured via PYDANTIC_AI_MODEL env var, or pass explicitly:
provider = PydanticAIProvider()  # uses PYDANTIC_AI_MODEL
provider = PydanticAIProvider(model="anthropic:claude-sonnet-4-6")
provider = PydanticAIProvider(model="ollama:llama3")

Reasoning models

Models that use internal chain-of-thought (OpenAI o1/o3, Qwen3, DeepSeek-R1) consume thinking tokens from the max_tokens budget. If extraction returns empty responses, increase the token budget:

# memory.toml
[extraction]
max_tokens = 8192

The default is 8192 to accommodate thinking tokens. Non-reasoning models work fine at this budget; no need to reduce it.

Requirements

• Python 3.12+
• PostgreSQL 17 with pgvector
• DATABASE_URL environment variable

License

MIT