XYZ-AI-Lab/AxisAgentic

AI repository intelligence

FR-AI / ANALYSIS

Why it is worth attention

It uniquely bridges agent execution and learning by preserving append-only traces that reconstruct the exact context visible to the model, enabling replay, evaluation, and state-faithful supervised fine-tuning from the same records.

Who it is for

AI researchers developing long-horizon agents
Developers building modular agent systems with tool orchestration
Teams needing reliable trajectory collection for supervised fine-tuning
Benchmark evaluators seeking reproducible agent evaluations

Use cases

Building and evaluating multi-turn search agents with context management and recovery
Collecting and exporting state-faithful trajectories for supervised fine-tuning of models
Replaying and debugging agent runs to understand model behavior at each step
Benchmarking agents across standard tasks with consistent evaluation harness

Strengths

Append-only trace design guarantees faithful reconstruction of model-visible context at all stages
Fully modular architecture allows swapping model clients, tools, orchestrators, datasets, and evaluators
Built-in support for long-run robustness: context budgets, compaction, rollback, retries, recovery, self-verification
Provides SFT exporters with runtime visibility markers and provenance for trajectory selection

Considerations

Requires Python 3.12+ and an OpenAI-compatible endpoint, restricting deployment on older or non-standard environments
Does not include model weights; users must provide their own models and endpoints
Reference recipes are currently focused on search (Web Search, WideSearch); general-purpose and coding agent recipes may be less mature

README quick start

English · 简体中文

XYZ AI Lab ·
Technical Report

AxisAgentic is an extensible runtime for long-horizon AI agents. It also collects the trajectories produced during execution. The runtime works with OpenAI-compatible endpoints and pluggable local model clients, and handles multi-turn execution, tool orchestration, context management, recovery, and benchmark evaluation. Each trace preserves the state visible to the model, so the same record can support recovery and replay, benchmark evaluation, or filtered SFT export.

Web Search and WideSearch are the current reference recipes. The same extension points can support domain, general-purpose, and coding agents. This repository does not include model weights.

✨ Core capabilities

Append-only traces preserve runtime events and reconstruct the context visible to the model at any stage.
Model clients, tools, orchestrators, datasets, evaluators, reward functions, and recipe policies are replaceable.
Context budgets, compaction, rollback, retries, recovery, self-verification, and tool limits support long runs.
Each task records traces, token and timing metrics, evaluation artifacts, and provenance for trajectory selection.
SFT exporters replay runtime visibility markers, while rollout interfaces connect execution to external training systems.
Strict YAML schemas and portable path schemes keep runs reproducible across environments.

🔁 From execution to learning

Every task writes an append-only trace. The trace is the common source for replay, evaluation, and trajectory collection. Selected trajectories can then be exported for external training.

Runtime markers record rollback, context compaction, and discard-all events. Replaying them reconstructs what the model saw at a given stage. Trace inspection and SFT export use the same rules, so supervised examples exclude hidden history and rolled-back actions.

Recipe exporters emit Swift Agent and related training formats with the source trace, task status, and optional metadata. The external training pipeline owns final correctness filters, loss masks, and optimization. AxisAgentic supplies the replay and export boundary so inference and training use the same interaction history.

🦅 Flagship reference: XYZ-Aquila

XYZ-Aquila is a search system built with AxisAgentic. Its recipe combi

Description

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

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo

Featured

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents

2,390

slvDev

Featured

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models

1,960

littledivy

Featured

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning

1,482