# openairymax/agentrt

Airymax AgentRT Transcend context limits. Achieve near-infinite memory.

Repository: https://github.com/openairymax/agentrt
Canonical: https://ross.abutalabs.com/products/agentrt
Homepage: https://atomgit.com/openairymax
Language: C
License: NOASSERTION
License Family: other
Topics: ai, os, assistant, own-your-data, non-langchain-wrapper
Last push: 2026-09-03T01:20:55+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 52, longevity 12
- inputs: {"age_days": 177, "days_push": 0, "days_rel": 108, "gap_med": null, "n_releases_24m": 1}
- flags: young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1265, forks 107 (observed 2026-09-03T02:15:15.747085+00:00)

## What it is
AgentRT is an OS-grade runtime platform for AI agent teams, providing primitives for orchestrating, scheduling, isolating, and observing agents, analogous to the JVM for languages or containerd for containers. It is a git superproject aggregating seven leaf repositories covering micro-core primitives, cognitive loops, memory stratification, security, IPC protocols, and gateway services.

## Use cases
- run teams of ai agents at scale with isolation and scheduling
- give ai agents near-infinite long-term memory
- self-host an agent runtime where i own my data
- orchestrate and observe long-running agent daemons
- build agent infrastructure without langchain
- secure multi-agent communication with ipc protocols

## When to choose
- you need low-level, OS-grade runtime infrastructure for multi-agent systems in C/C++
- you want data ownership and self-hosted agent memory
- you are building a custom agent platform and want foundational primitives rather than a high-level framework

## When to avoid
- you want a quick high-level agent framework in Python or TypeScript
- you need a mature, widely-adopted solution - the project is at version 0.1.1 with a nonstandard dual license
- you prefer batteries-included agent SDKs like LangChain or similar wrappers

## Facets
- artifact type: framework
- maturity: experimental
- function: agent-framework, concurrency, security, caching, rpc, monitoring, developer-tools
- domain: artificial-intelligence, large-language-models, developer-tools, microservices
- platform: cpp, c, self-hosted, cross-platform
- tags: agent-runtime, memory-management, git-submodules, monorepo, agentic-infrastructure, own-your-data, c11, cpp17, ai-agents, linux

## Member repositories
- openairymax/agentrt (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:15.747085+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:03:43.394582+00:00, confidence not recorded.
  - readme: https://github.com/openairymax/agentrt (fetched 2026-09-03T02:15:15.747085+00:00, sha f57796a72619)
- Data as of 2026-08-30T08:39:29.467469+00:00.