# XYZ-AI-Lab/AxisAgentic

AxisAgentic: An Extensible Runtime and Trajectory-Collection Framework for Long-Horizon Agents.

Repository: https://github.com/XYZ-AI-Lab/AxisAgentic
Canonical: https://ross.abutalabs.com/products/axisagentic
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-24T17:35:52+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 2
- inputs: {"age_days": 41, "days_push": 40, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1114, forks 142 (observed 2026-08-28T04:03:38.142966+00:00)

## What it is
AxisAgentic is an extensible Python runtime for long-horizon AI agents that handles multi-turn execution, tool orchestration, context management, and recovery. It records append-only traces of every run, which can be replayed, evaluated against benchmarks, or exported as SFT training trajectories.

## Use cases
- run long-horizon ai agents with tool orchestration
- collect agent trajectories for sft fine-tuning data
- replay and evaluate agent runs on benchmarks
- build custom agents with pluggable model clients and tools
- manage context compaction and recovery in multi-turn agent runs
- export filtered agent traces for external training systems

## When to choose
- you need reproducible, traceable execution of long-running agents
- you want to collect and export trajectories for model training
- you need pluggable model clients, tools, evaluators, and reward functions
- you run benchmark evaluations of agent behavior

## When to avoid
- you need a simple chatbot or single-turn LLM wrapper
- you want bundled model weights - the repo includes none
- you need a production end-user agent product rather than a research/runtime framework
- you are not working in Python 3.12+ environments

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, benchmarking, data-generation, workflow-automation
- domain: large-language-models, machine-learning, developer-tools
- platform: python, cli
- tags: trajectory-collection, long-horizon-agents, sft-data, agent-runtime, replay, openai-compatible, tool-orchestration, ai-agents, linux, macos

## Member repositories
- XYZ-AI-Lab/AxisAgentic (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.142966+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 2026-08-30T06:42:13.205853+00:00, confidence not recorded.
  - readme: https://github.com/XYZ-AI-Lab/AxisAgentic (fetched 2026-08-28T04:03:38.142966+00:00, sha 5c5e7c62591d)
- Data as of 2026-08-30T08:39:29.467469+00:00.