contexara 2.3.0

AI that forgets is just autocomplete. Contexara gives your agent a memory it can build on.

Contexara

AI that forgets is just autocomplete. Contexara gives your agent a memory it can build on.

Persistent, three-tier memory layer for AI agents. Drop it in and your agent remembers facts, preferences, and past sessions — automatically, across every conversation.

---

Install

pip install contexara
contexara setup
contexara ask "what was I working on?"

For specific providers:

pip install contexara[openai]
pip install contexara[anthropic]
pip install contexara[gemini]
pip install contexara[all-providers]

---

How It Works

Tier	What	Scope
T1 — Raw Turns	Every user/assistant message, stored verbatim	Current session
T2 — Episodes	LLM-crystallized summaries of past sessions	Cross-session
T3 — Semantic Memory	Extracted facts, preferences, constraints, corrections	Permanent

On every query, all three tiers inject context automatically — your agent is never blind.

---

Supported Providers

Provider	CONTEXARA_PROVIDER value
AWS Bedrock	bedrock (default)
OpenAI	openai
Anthropic	anthropic
Google Gemini	gemini
OpenRouter	openrouter

Configure via contexara setup or manually in ~/.contexara/.env:

CONTEXARA_PROVIDER=openai
CONTEXARA_MODEL=gpt-4o
OPENAI_API_KEY=sk-...

---

Python SDK

from contexara import ContextaraClient

mem = ContextaraClient(namespace="my-agent")

# Load session context (T1 turns + T2 episode anchor)
ctx = mem.context(n=20)

# Memory stats
stats = mem.stats()

# Force crystallize current session
mem.checkpoint()

Build Your Own Agent

from contexara import ContextaraClient
from contexara.retrieve import retrieve, retrieve_episodes
from contexara.enhance import enhance
from contexara.llm import call_llm
from contexara.ingest import ingest_turn, flush_extraction

NAMESPACE = "my-agent"
mem = ContextaraClient(namespace=NAMESPACE)

ctx = mem.context(n=20)
session_id = ctx["session_id"]
episode_anchor = ctx.get("episode_summary")
recent_turns = ctx.get("turns", [])

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in ("exit", "quit"):
        flush_extraction(session_id, namespace=NAMESPACE)
        break

    memories = retrieve(user_input, top_k=5, namespace=NAMESPACE)
    episode_hits = retrieve_episodes(user_input, top_k=3, namespace=NAMESPACE)

    prompt = enhance(
        user_input,
        memories,
        recent_turns=recent_turns or None,
        episode_anchor=episode_anchor,
        episode_hits=episode_hits or None,
    )

    reply = call_llm(prompt)
    print(f"Assistant: {reply}")

    recent_turns.append({"role": "user", "content": user_input})
    recent_turns.append({"role": "assistant", "content": reply})

    ingest_turn(user_input, reply, session_id=session_id, namespace=NAMESPACE)
    episode_anchor = None

---

CLI Reference

Command	Description
contexara setup	Configure AI provider credentials
contexara ask "<query>"	Single query with full memory context
contexara chat	Interactive chat mode
contexara store "<text>"	Save a memory directly
contexara list	List stored memories
contexara search "<query>"	Semantic search over memories
contexara stats	Memory counts by kind and source
contexara consolidate	LLM-merge overlapping memories
contexara clear	Delete all memories in namespace
contexara namespace list|create|switch|delete	Manage namespaces
contexara serve	Start REST API server
contexara dashboard	Start web dashboard
contexara mcp	Start MCP server

---

Namespaces

Complete data isolation between agents or projects:

contexara namespace create work
contexara namespace switch work
contexara ask "what are my pending tasks?" --namespace work

---

Key Features

• Local first — all data in ~/.contexara/, no cloud required
• LLM agnostic — Bedrock, OpenAI, Anthropic, Gemini, OpenRouter
• Batch extraction — memories extracted every 10 turns for cost efficiency, flushed on exit
• Intent classification — detects historical vs. recent vs. semantic queries, adjusts retrieval strategy
• Hybrid retrieval — FTS5 + cosine vector search with RRF fusion
• Session continuity — sessions crystallize after 60 min inactivity, injected on next session start
• Never-delete versioning — full history of every memory update
• Cold archive — turns older than 30 days auto-swept to FTS5-searchable archive
• MCP server — plug into Claude Desktop or any MCP-compatible framework
• Web dashboard — memory browser, session explorer, latency charts, LLM-as-judge evals

---

Data Storage

~/.contexara/
├── memory.db          # T3 semantic memories
├── active_state.db    # T1 raw turns + T2 episodes + sessions
└── cold_archive.db    # archived turns older than 30 days

---

Built by Prajwal Narayan