recollect 0.5.0

Human-like memory for AI applications

recollect

Cognitive memory system for AI applications. Activation-based retrieval with time decay, spreading activation, and token-budgeted recall.

Install

pip install recollect                 # Includes Anthropic provider
pip install recollect[openai]         # Adds OpenAI/OpenAI-compatible provider support
pip install recollect[pydantic-ai]    # Adds pydantic-ai multi-provider support

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.
ANTHROPIC_API_KEY	For Anthropic provider	--	Anthropic API key. SDK resolves automatically.
OPENAI_API_KEY	For OpenAI provider	--	OpenAI API key. Required by OpenAIProvider.
ANTHROPIC_MODEL	No	claude-haiku-4-5-20251001	Override default Anthropic extraction model.
OPENAI_MODEL	No	gpt-5-mini	Override default OpenAI extraction model.
OLLAMA_MODEL	No	qwen3.5	Override default Ollama extraction model.
ANTHROPIC_BASE_URL	No	api.anthropic.com	Override Anthropic API endpoint.
OPENAI_BASE_URL	No	api.openai.com	Override OpenAI API endpoint.
OLLAMA_BASE_URL	No	http://localhost:11434/v1	Ollama API endpoint.
PYDANTIC_AI_MODEL	No	--	pydantic-ai model string in provider:model format (e.g., ollama:ministral-3, anthropic:claude-haiku-4-5-20251001).
MEMORY_EXTRACTION_MAX_TOKENS	No	4096	Max tokens for LLM extraction. Increase for reasoning models that consume thinking tokens.
OPENAI_REASONING_EFFORT	No	low	Reasoning effort for OpenAI structured output (low, medium, high).
OPENAI_STRUCTURED_MAX_TOKENS	No	1024	Token cap for OpenAI structured output. Reasoning tokens consume this budget.
MEMORY_CONFIG	No	--	Path to custom TOML config file.
MEMORY_EXTRACTION_INSTRUCTIONS	No	--	Override extraction prompt instructions.
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	0.3	Min cosine similarity to consider a trace as related.
MEMORY_RECALL_TOKENS_STRENGTH_THRESHOLD	No	0.1	Min token strength to activate at query time.
MEMORY_RECALL_TOKENS_SCORE_BONUS	No	0.1	Gated additive bonus: token_strength * bonus * effective_sim.
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.

Configuration

Defaults ship in config.toml. Override by placing a memory.toml in your working directory, or set MEMORY_CONFIG to a custom path. Only include keys you want to change:

[memory]
decay_rate = 0.05

[retrieval]
max_retrievals = 10

[extraction]
max_tokens = 2048
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, openai_reasoning_effort, openai_structured_max_tokens
[embedding]	Local embedding model	model, dimensions
[persona]	Persona fact management	auto_extract, confidence_threshold
[session]	Session summaries	summary_strength, summary_max_tokens

Full defaults: config.toml

Or pass a path directly:

from recollect.config import MemoryConfig

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

LLM Providers

Four providers behind the LLMProvider protocol. The first three share the same constructor signature: (model, api_key, base_url, defaults).

Anthropic (default)

from recollect.llm.anthropic import AnthropicProvider
from recollect.extraction import PatternExtractor

provider = AnthropicProvider()  # uses ANTHROPIC_API_KEY
extractor = PatternExtractor(provider)
memory = CognitiveMemory(extractor=extractor)

OpenAI

Requires pip install recollect[openai].

from recollect.llm.openai import OpenAIProvider

provider = OpenAIProvider()  # uses OPENAI_API_KEY

Ollama / LM Studio (OpenAI-compatible)

from recollect.llm.openai_compat import OpenAICompatProvider

# Ollama
provider = OpenAICompatProvider(
    model="qwen3.5",
    base_url="http://localhost:11434/v1",
)

# LM Studio
provider = OpenAICompatProvider(
    model="your-model",
    base_url="http://localhost:1234/v1",
)

pydantic-ai (multi-provider)

Requires pip install recollect[pydantic-ai]. Routes calls through pydantic-ai's Agent abstraction, giving access to 20+ model providers through a single dependency.

The model string uses pydantic-ai format (provider:model). Credentials are read from the environment by the underlying provider (e.g., ANTHROPIC_API_KEY for Anthropic, OLLAMA_BASE_URL for Ollama). Provider-specific model overrides like OLLAMA_MODEL or ANTHROPIC_MODEL are not used -- the model is embedded in PYDANTIC_AI_MODEL.

from recollect.llm.pydantic_ai import PydanticAIProvider

# Anthropic via pydantic-ai
provider = PydanticAIProvider(model="anthropic:claude-haiku-4-5-20251001")

# Ollama via pydantic-ai (reads OLLAMA_BASE_URL from env)
provider = PydanticAIProvider(model="ollama:ministral-3")

# OpenAI via pydantic-ai
provider = PydanticAIProvider(model="openai:gpt-4o")

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 4096, which provides sufficient headroom for most models.

Requirements

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

License

MIT