Skip to main content

Complete AI memory, routing, safety, and context management suite

Project description

Antaris Suite v3.1.0

Agent infrastructure for intelligent, secure, and memory-persistent AI systems.

v3.1.0 — Discord message bridge • Compaction hook fixes • Phase 4 roadmaps • All 6 modules consolidated under single canonical repo

Packages

Package Version Description
antaris-memory 3.1.0 Persistent memory system with BM25 search, WAL, sharding, and Discord bridge
antaris-router 4.1.0 Intelligent model routing with cost tracking, confidence gating, and A/B testing
antaris-guard 3.1.0 Prompt injection detection, reputation tracking, and rate limiting
antaris-context 3.1.0 Context compression, summarization, and relevance scoring
antaris-pipeline 3.1.0 Agent orchestration pipeline with telemetry and OpenClaw integration
antaris-contracts 1.1.0 Versioned state schemas, failure semantics, and debug CLI
antaris-openclaw-plugin 1.0.0 OpenClaw plugin — auto-recall and auto-ingest via lifecycle hooks

Architecture

antaris-openclaw-plugin   (lifecycle hooks — auto-recall + auto-ingest)
        │
antaris-pipeline          (orchestration)
   ┌────┴────────────────────┐
antaris-memory         antaris-router      antaris-guard      antaris-context
(persistence)          (model selection)   (security)         (compression)

Design Principles

  • Zero external dependencies on all core Python packages — stdlib only
  • File-based persistence — no database required
  • Multi-process safe — cross-platform FileLock using os.mkdir() atomicity
  • MCP-compatible — memory and router expose MCP servers
  • Fully tested — 835 tests, 3 external security reviews (Opus 4.6, GPT-5.2, Gemini Pro)

Installation

# Install each package
pip install -e antaris-memory
pip install -e antaris-router
pip install -e antaris-guard
pip install -e antaris-context
pip install -e antaris-pipeline

# Install OpenClaw plugin
openclaw plugins install --link antaris-openclaw-plugin
openclaw plugins enable antaris-memory

What's New in v3.1.0

  • 🔗 Discord Message Bridge — automatic ingestion of Discord messages into antaris-memory with message_in hook
  • 🛡️ Compaction Hook Fixes — 5s timeout + 30s watchdog for bridge health, auto-restart on failure
  • 📋 Phase 4 Roadmaps — documented future directions for all 6 packages (v4.0+ features)
  • 📦 Full Consolidation — all modules now subrepos under antaris-suite (canonical source)
  • 🧪 1,508 Total Tests — across all packages, all passing locally and on CI

Release

v3.1.0 — All 4 external reviews passed (Claude Opus/GPT/Gemini/Shiro). Production-ready for enterprise deployment with full OpenClaw integration.

See docs/MANIFEST.json for SHA-256 integrity verification of all source files across 6 packages.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

antaris_suite-4.0.3.tar.gz (28.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

antaris_suite-4.0.3-py3-none-any.whl (8.1 kB view details)

Uploaded Python 3

File details

Details for the file antaris_suite-4.0.3.tar.gz.

File metadata

  • Download URL: antaris_suite-4.0.3.tar.gz
  • Upload date:
  • Size: 28.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for antaris_suite-4.0.3.tar.gz
Algorithm Hash digest
SHA256 90504abae06cfea80eadb8210e0631f680fd609eb9612fe043fd92f869b719f3
MD5 5de8ea9ebc855ea82f14e9933ee5ac5c
BLAKE2b-256 9cc85f408ee12af999e635d96a2fef7ea0d7a47ceff7c8e99528fd0803b8586d

See more details on using hashes here.

File details

Details for the file antaris_suite-4.0.3-py3-none-any.whl.

File metadata

  • Download URL: antaris_suite-4.0.3-py3-none-any.whl
  • Upload date:
  • Size: 8.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for antaris_suite-4.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 3272ee9c5ae5d3f2b0e57782fb088863ee833de907ce52e1c047d1ca3713d22d
MD5 248ff92dad603a32c9e4c51431afbcb1
BLAKE2b-256 81d204d101a3b96e17433fe1c36e603c94dd9287c3bd42b6c9aceff6b4fc7536

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page