FrontierAgent
π§© FrontierAgent, our agent framework, open-sourced alongside it β native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no prein
What is FrontierAgent?
π§© FrontierAgent, our agent framework, open-sourced alongside it β native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
Overview of FrontierAgent
What it is
FrontierAgent is an open-source agent runtime, terminal product, and evaluation suite for long-horizon research and file-based work. The frontier-agent TUI ships two native workflows: ReAct (one stateful agent researches, reads files, writes deliverables, runs commands, and iterates in a task-scoped sandbox) and Agent Team (a coordinator maintains a task board, delegates independent work to parallel sub-agents, collects their reports, and synthesizes the result). The same workflow engine powers the benchmark runner used to evaluate Apodex models. The framework, tools, workflows, and evaluation layer remain separate, so each can be reused independently.
Key features
- Native Agent Team workflow. The coordinator decomposes the request, dispatches bounded parallel assignments, receives structured reports, and can use an optional fast reporter for final evidence review.
- Task Board. Agent Team's
add_taskandupdate_taskevents appear live in the TUI sidebar with pending, active, completed, blocked, and cancelled state. - Sandboxed file work. Shell and file tools share one task-scoped filesystem:
/inputsis read-only,/workspaceis working state, and/outputscontains persistent deliverables. Authorization and sandbox failures are fail-closed. - Asynchronous intervention. Type while an agent is running to queue a new instruction. It is injected at the next safe turn boundary without discarding the active run. In Agent Team mode it steers the coordinator; already-running sub-agents are allowed to finish.
- Transparent deliverables. On macOS/Docker,
/outputsmaps to.apodex/runs//outputson the host. The same run directory also contains its checkpoint, trace, engine log, and trajectories. - Approval, trace, and recovery. Mutating operations show a diff and require approval unless
--yesis enabled. Sessions are checkpointed, every action is traced locally,/revertrestores session changes, and--resumecontinues a saved run. - Evaluation included. The subprocess runner supports research and file-grounded benchmarks, deterministic artifact collection, concurrency, progress inspection, and rerunning individual failures.
Use cases
- Long-horizon research tasks that require iterative reading, writing, and command execution.
- File-based work with sandboxed inputs, workspace, and outputs.
- Running agent teams for parallel sub-task delegation and synthesis.
- Evaluating models on research and file-grounded benchmarks (e.g., FrontierSearchBench, FrontierChallenge).
- Local development and testing of agent workflows with an OpenAI-compatible endpoint.
Getting started
Requirements: Git, Python 3.12, uv, and an OpenAI-compatible model endpoint. Docker is optional. bash git clone https://github.com/ApodexAI/FrontierAgent.git cd FrontierAgent uv sync --python 3.12 --extra dev cp .env.example .env Add your endpoint to .env: dotenv OPENAI_API_KEY=your-key OPENAI_BASE_URL=https://your-openai-compatible-endpoint/v1 OPENAI_MODEL=your-model-name Start the TUI: bash # Stateful single-agent workflow uv run frontier-agent --mode react --cwd /path/to/project # Coordinator plus parallel sub-agents uv run frontier-agent --mode agent_team --cwd /path/to/project
License and pricing
Licensed under Apache-2.0. Open source and free to use.
Based on the project's public README and repository metadata.