# esengine/deepseek-reasonix

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/esengine-deepseek-reasonix).**

24,096 stars · 1,467 forks · Go · MIT

## Links

- GitHub: https://github.com/esengine/DeepSeek-Reasonix
- Homepage: http://reasonix.io/
- awesome-repositories: https://awesome-repositories.com/repository/esengine-deepseek-reasonix.md

## Topics

`agent` `agent-framework` `ai-agent` `ai-coding` `cli` `coding-agent` `deepseek` `developer-tools` `ink` `llm` `prompt-caching` `r1` `terminal` `tool-use` `tui` `typescript`

## Description

DeepSeek-Reasonix is an autonomous software engineering framework and terminal-based AI IDE designed to coordinate large language models for complex programming tasks. It functions as a multi-session agent that utilizes a split planner and executor workflow to break down and implement technical objectives.

The system distinguishes itself through a specialized focus on session optimization and extensibility. It employs prefix caching and append-only history to reduce token consumption and latency during long sessions. It further extends its capabilities by integrating external tool servers via the Model Context Protocol and managing third-party plugins as JSON-RPC subprocesses.

The project includes a comprehensive safety and management layer featuring workspace-rooted file sandboxing and hierarchical tool permission gating. It maintains project awareness through codebase context indexing and markdown-based persistent memory, while providing state restoration via code snapshots. Users can manage these autonomous workflows through a command line interface or a local web-based dashboard.

## Tags

### Artificial Intelligence & ML

- [AI Terminal Assistants](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-terminal-assistants.md) — An AI-powered terminal assistant that coordinates planning and execution for automated programming tasks.
- [Terminal AI Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/terminal-ai-interfaces.md) — Provides a terminal-based AI interface for interactive development tasks, paired with a local web management dashboard.
- [Model Context Protocol](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/model-context-protocol.md) — Connects to Model Context Protocol servers via stdio or HTTP to extend AI capabilities with external tools. ([source](http://reasonix.io/docs/))
- [Autonomous Coding Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-coding-assistants/autonomous-coding-agents.md) — Functions as an autonomous coding agent that decomposes complex tasks into actionable steps for execution.
- [Autonomous Programming Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-programming-execution.md) — Provides a terminal harness that allows AI models to autonomously execute programming work. ([source](https://cdn.jsdelivr.net/gh/esengine/deepseek-reasonix@main-v2/README.md))
- [Autonomous Software Engineers](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-software-engineers.md) — Operates as an autonomous software engineer that coordinates separate planner and executor agents for complex technical tasks.
- [MCP Protocol Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-integrations/mcp-protocol-integrations.md) — Integrates external services and tools via the Model Context Protocol for standardized AI tool access.
- [Codebase Context Indexing](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-knowledge-bases/codebase-context-indexing.md) — Provides codebase context indexing to create grounded knowledge bases for AI agent awareness.
- [Multi-Model Workflow Coordinators](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-model-workflow-coordinators.md) — Implements a framework that sequences a planner and executor model to solve complex technical tasks. ([source](https://cdn.jsdelivr.net/gh/esengine/deepseek-reasonix@main-v2/README.md))
- [Planner-Actor Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/planner-actor-architectures.md) — Decomposes high-level goals into a sequence of subtasks using a distinct planner and executor session architecture.
- [Agentic Research Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-research-strategies.md) — Executes multi-phase objectives through an automated research strategy with detailed iteration logging. ([source](http://reasonix.io/docs/))
- [Markdown-Based Project Memory](https://awesome-repositories.com/f/artificial-intelligence-ml/instructional-prompting/hierarchical-instruction-resolvers/markdown-based-project-memory.md) — Stores persistent project facts and session history in human-readable markdown files for AI context.
- [Prefix Caching](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-caching/prefix-caching.md) — Optimizes token consumption and latency by using append-only history and prefix caching for long sessions.
- [Subagent Orchestrations](https://awesome-repositories.com/f/artificial-intelligence-ml/subagent-orchestrations.md) — Deploys specialized helper agents for research and security reviews using isolated toolsets. ([source](https://esengine.github.io/DeepSeek-Reasonix/))
- [Tool Server Registries](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-server-registries.md) — Merges tools from external servers using standard input, server-sent events, or HTTP into a single prefixed registry. ([source](https://esengine.github.io/DeepSeek-Reasonix/))

### Development Tools & Productivity

- [Autonomous Coding Workflows](https://awesome-repositories.com/f/development-tools-productivity/agentic-workflow-integrations/autonomous-coding-workflows.md) — Implements autonomous coding workflows that allow AI agents to iteratively edit code, run tests, and refine implementations.
- [AI Coding Assistants](https://awesome-repositories.com/f/development-tools-productivity/ai-coding-assistants.md) — Provides a terminal-based AI coding environment with integrated tool approval and file referencing. ([source](http://reasonix.io/docs/))
- [Task Sandboxing](https://awesome-repositories.com/f/development-tools-productivity/execution-sandboxes/task-sandboxing.md) — Implements task sandboxing that restricts write access to a specific workspace and requires human approval. ([source](https://esengine.github.io/DeepSeek-Reasonix/))
- [Agentic Task Orchestration](https://awesome-repositories.com/f/development-tools-productivity/task-automation-tools/agentic-task-orchestration.md) — Orchestrates autonomous agent workflows for iterative execution of complex development tasks.

### Security & Cryptography

- [Tool Execution Permissions](https://awesome-repositories.com/f/security-cryptography/permission-based-access-control/tool-execution-permissions.md) — Gates tool calls using a hierarchy of rules to prevent unauthorized system modifications by the agent. ([source](http://reasonix.io/docs/))
- [File System Access Controls](https://awesome-repositories.com/f/security-cryptography/security/policies/host-resource-access/file-system-access-controls.md) — Enforces workspace-rooted file sandboxing to restrict tools from modifying files outside a designated directory. ([source](http://reasonix.io/docs/))
- [Agentic Session Persistence](https://awesome-repositories.com/f/security-cryptography/identity-access-management/session-management/stateful-session-persistence/agentic-session-persistence.md) — Tracks task progress in external files to allow AI agents to resume work across sessions. ([source](https://esengine.github.io/DeepSeek-Reasonix/))

### Data & Databases

- [Sandboxed File Systems](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-persistence-storage/data-storage/file-based-storage/local-file-storage/sandboxed-file-systems.md) — Restricts the AI agent's filesystem access to a specific workspace root for security.

### Networking & Communication

- [JSON-RPC Implementations](https://awesome-repositories.com/f/networking-communication/json-rpc-implementations.md) — Integrates external plugins as separate subprocesses using the JSON-RPC protocol.
- [MCP Transport Protocol Supports](https://awesome-repositories.com/f/networking-communication/network-transport-protocols/multi-protocol-transport-abstraction/mcp-transport-protocol-supports.md) — Supports multiple communication channels including stdio, SSE, and HTTP for connecting to external tool servers.

### Software Engineering & Architecture

- [Third-Party Plugins](https://awesome-repositories.com/f/software-engineering-architecture/integration-extensibility/extensibility/third-party-plugins.md) — Integrates third-party plugins as JSON-RPC subprocesses to extend the system's functional capabilities. ([source](https://cdn.jsdelivr.net/gh/esengine/deepseek-reasonix@main-v2/README.md))

### System Administration & Monitoring

- [Token Cost Optimizations](https://awesome-repositories.com/f/system-administration-monitoring/usage-monitoring/token-usage-analytics/token-consumption-trackers/token-cost-optimizations.md) — Decreases operational costs and latency using append-only history and prefix caching to optimize token usage. ([source](https://esengine.github.io/DeepSeek-Reasonix/))