Plandex
Plandex is an open-source, terminal-based AI coding agent designed to take on large, multi-step software development tasks across many files in real world codebases. Written in Go and released under the MIT license, Plandex builds and executes long-running "plans" — durable, branchable units of work that combine intelligent context management, project maps generated with tree-sitter for 30+ programming languages, an effective 2M-token context window, and a cumulative diff review sandbox that isolates AI edits until a developer explicitly applies them. The tool ships as a CLI with an interactive REPL (fuzzy auto-complete), supports automated debugging of terminal commands and browser applications, integrates with Git for branching and commit-message generation, and is provider-neutral — working with Anthropic Claude, OpenAI, Google Gemini, OpenRouter.ai, Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, Ollama, and any OpenAI-compatible custom provider. The Plandex Server exposes a REST management/orchestration API (over 60 endpoints across accounts, orgs, projects, plans, branches, context, conversation, diffs, settings, model packs, and streaming execution) that powers both the CLI/REPL and the hosted Plandex Cloud. Plandex Cloud is winding down as of 2025-10-03; Plandex is now distributed primarily as a Docker-based self-hosted / local-mode product that users run with their own model-provider API keys.
1 APIs
2 Capabilities
16 Features
AIAI Coding AgentDeveloper ToolsOpen SourceCLITerminalLLMCoding AssistantAgentsGoContext ManagementPlansSelf-HostedREST
Run Capabilities with Naftiko — Deploy and orchestrate these API capabilities using Naftiko Fleet.
Run with Naftiko
Run Capabilities with Naftiko — Deploy and orchestrate these API capabilities using Naftiko Fleet.
Run with Naftiko
2M-Token Effective Context Window
Smart context management loads only what's needed per step, enabling reliable work in large projects and files.
Tree-Sitter Project Maps
Fast project map generation and syntax validation across 30+ programming languages. Indexes directories with 20M+ tokens.
Cumulative Diff Sandbox
AI-generated changes are isolated from project files until explicitly applied, with cumulative review and roll-back.
Configurable Autonomy
Five autonomy levels — None, Basic, Plus, Semi-Auto, Full-Auto — selectable per-plan or via CLI flags.
Automated Debugging
Repeatedly runs commands (builds, tests, lints, scripts) and auto-fixes failures with rollback. Also debugs browser apps via Chrome.
Model Packs
Curated combinations of models bound to internal roles (planner, coder, builder, summarizer, verifier, context loader); built-in packs for daily, reasoning, strong, cheap, oss, and planner-specialized variants.
Multi-Provider Support
First-class support for Anthropic, OpenAI, Google AI Studio, Google Vertex AI, Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, OpenRouter, Ollama, and any OpenAI-compatible custom provider.
Claude Pro/Max Subscription
Plandex can use a Claude Pro or Max subscription as the credential when calling Anthropic models.
Context Caching
Built-in context caching across OpenAI, Anthropic, and Google models reduces latency and cost on multi-step plans.
Plan Version Control
Every plan update is versioned, with branching for exploring multiple paths or comparing different models. Rewind to any prior SHA.
Git Integration
Commit message generation, optional auto-commits, and clean integration with project git history.
REPL with Fuzzy Auto-Complete
Interactive shell launched by `plandex` (or `pdx`) with fuzzy command and file completion; backslash equivalents (`\new`, `\tell`) for every command.
One-Line Install
Zero-dependency CLI install via `curl -sL https://plandex.ai/install.sh | bash`. Docker compose for the self-hosted server.
Background Tasks
`--bg` flag runs plans concurrently in the background under separate streams.
Smart Context + Auto-Load Context
Loads only the files needed for each implementation step (smart-context) and uses the project map to choose them (auto-load-context).
Streaming Plan Execution
tell, build, and connect endpoints stream model responses live; clients can reconnect to in-progress plans after disconnects.
Large Refactors
Coordinate refactors that touch dozens of files across a large codebase without losing the thread between steps.
Polyglot Project Work
Work in repositories that span 30+ languages thanks to tree-sitter project maps.
Adding Features To Real Projects
Take a feature from idea through chat mode, into a detailed implementation plan, into reviewed and applied file changes.
Automated Debugging
Wrap a flaky build, test, or browser app in `plandex debug` and let Plandex iteratively repair it.
Codebase Onboarding And Q&A
Use chat mode and the project map to ask questions about an unfamiliar codebase.
Multi-Model Comparisons
Branch a plan to run different model packs against the same context and compare results.
Long-Running Background Coding
Kick off `--bg` plans, switch repos, and reconnect to streaming output later.
BYO Subscription Coding Agent
Use a Claude Pro/Max subscription as the credential for an autonomous coding agent.
Self-Hosted AI Coding For Sensitive Codebases
Run the Plandex server in Docker on-prem with locally-hosted Ollama models or a private custom provider.
Anthropic Claude
Direct Anthropic API integration; also supports Claude Pro/Max subscriptions.
OpenAI
Direct OpenAI API integration via OPENAI_API_KEY.
OpenRouter.ai
Default recommended provider for self-hosted Plandex; also used as a failover route across other configured providers.
Google AI Studio
Gemini models via GEMINI_API_KEY.
Google Vertex AI
Gemini and Anthropic models via Vertex AI credentials.
Microsoft Azure OpenAI
OpenAI models on Azure with deployment-name mapping.
AWS Bedrock
Anthropic models on Bedrock with AWS profile or env-var credentials.
DeepSeek
DeepSeek models via DEEPSEEK_API_KEY.
Perplexity
Perplexity models via PERPLEXITY_API_KEY.
Ollama
Local model hosting via Ollama; no API keys required.
Custom Providers
Any OpenAI-compatible API can be added via a JSON config (`plandex models custom`).
Relace
Instant-apply fallback model used when Plandex cannot apply edits deterministically (Plandex Cloud).
Git
Branching, commit-message generation, optional auto-commits.
Chrome
Automated debugging of browser applications when Chrome is installed.
Docker
Self-hosted server distributed as a Docker image with a published docker-compose stack.
Postgres
Backing database for the Plandex server.
LiteLLM Proxy
Embedded LiteLLM proxy used by the server to talk to model providers uniformly.
Stripe
Payment processing for Plandex Cloud subscriptions and credit purchases.
Loops
Email marketing for Plandex updates (Plandex Cloud).
Google Analytics
Basic usage analytics (Plandex Cloud).
Rollbar
Error tracking (Plandex Cloud).
aid: plandex
name: Plandex
description: >-
Plandex is an open-source, terminal-based AI coding agent designed to take
on large, multi-step software development tasks across many files in real
world codebases. Written in Go and released under the MIT license, Plandex
builds and executes long-running "plans" — durable, branchable units of
work that combine intelligent context management, project maps generated
with tree-sitter for 30+ programming languages, an effective 2M-token
context window, and a cumulative diff review sandbox that isolates AI
edits until a developer explicitly applies them. The tool ships as a CLI
with an interactive REPL (fuzzy auto-complete), supports automated
debugging of terminal commands and browser applications, integrates with
Git for branching and commit-message generation, and is provider-neutral
— working with Anthropic Claude, OpenAI, Google Gemini, OpenRouter.ai,
Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, Ollama, and any
OpenAI-compatible custom provider. The Plandex Server exposes a REST
management/orchestration API (over 60 endpoints across accounts, orgs,
projects, plans, branches, context, conversation, diffs, settings, model
packs, and streaming execution) that powers both the CLI/REPL and the
hosted Plandex Cloud. Plandex Cloud is winding down as of 2025-10-03;
Plandex is now distributed primarily as a Docker-based self-hosted /
local-mode product that users run with their own model-provider API keys.
type: Index
position: Provider
access: 3rd-Party
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
- AI
- AI Coding Agent
- Developer Tools
- Open Source
- CLI
- Terminal
- LLM
- Coding Assistant
- Agents
- Go
- Context Management
- Plans
- Self-Hosted
- REST
url: https://raw.githubusercontent.com/api-evangelist/plandex/refs/heads/main/apis.yml
created: '2026-05-25'
modified: '2026-05-29'
specificationVersion: '0.20'
apis:
- name: Plandex Server API
description: >-
Management and orchestration REST API exposed by the Plandex server
(open-source, Go) used by the Plandex CLI/REPL to drive long-running
coding plans across organizations, projects, plans, branches, context,
conversation, model packs, and configuration. The same API powered
Plandex Cloud (winding down 2025-10-03) and now powers self-hosted /
local-mode deployments via Docker. Default local-mode bind is
http://localhost:8099.
humanURL: https://docs.plandex.ai/development
baseURL: http://localhost:8099
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
- AI Coding Agent
- Plans
- REST
- Self-Hosted
properties:
- type: Documentation
url: https://docs.plandex.ai
- type: SourceCode
url: https://github.com/plandex-ai/plandex/tree/main/app/server
- type: OpenAPI
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/openapi/plandex-server-openapi.yml
- type: JSONSchema
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-schema/plandex-server-plan-schema.json
- type: JSONSchema
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-schema/plandex-server-context-item-schema.json
- type: JSONSchema
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-schema/plandex-server-branch-schema.json
- type: JSONSchema
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-schema/plandex-server-convo-message-schema.json
- type: JSONSchema
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-schema/plandex-server-model-pack-schema.json
- type: JSONSchema
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-schema/plandex-server-plan-config-schema.json
- type: JSONStructure
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-structure/plandex-server-plan-structure.json
- type: JSONStructure
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-structure/plandex-server-context-item-structure.json
- type: JSONStructure
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-structure/plandex-server-model-pack-structure.json
- type: Example
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/examples/plandex-server-plan-example.json
- type: Example
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/examples/plandex-server-context-item-example.json
- type: Example
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/examples/plandex-server-convo-message-example.json
- type: Example
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/examples/plandex-server-model-pack-example.json
- type: Example
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/examples/plandex-server-plan-config-example.json
- type: Authentication
url: https://docs.plandex.ai/hosting/self-hosting/local-mode-quickstart
description: Bearer token issued by the sign-in flow; CLI handles token persistence.
common:
- type: Website
url: https://plandex.ai
- type: Documentation
url: https://docs.plandex.ai
- type: GettingStarted
url: https://docs.plandex.ai/quick-start
- type: Quickstart
url: https://docs.plandex.ai/hosting/self-hosting/local-mode-quickstart
- type: Install
url: https://plandex.ai/install.sh
- type: GitHub
url: https://github.com/plandex-ai/plandex
- type: GitHubOrganization
url: https://github.com/plandex-ai
- type: GitHubRepository
url: https://github.com/plandex-ai/plandex
- type: SourceCode
url: https://github.com/plandex-ai/plandex
- type: License
url: https://github.com/plandex-ai/plandex/blob/main/LICENSE
- type: CLI
url: https://docs.plandex.ai/cli-reference
- type: REPL
url: https://docs.plandex.ai/repl
- type: Pricing
url: https://docs.plandex.ai/hosting/cloud
- type: PrivacyPolicy
url: https://plandex.ai/privacy
- type: TermsOfService
url: https://plandex.ai/terms
- type: Security
url: https://docs.plandex.ai/security
- type: Blog
url: https://plandex.ai/blog
- type: ReleaseNotes
url: https://github.com/plandex-ai/plandex/releases
- type: ChangeLog
url: https://github.com/plandex-ai/plandex/releases
- type: Support
url: https://github.com/plandex-ai/plandex/issues
- type: Discord
url: https://discord.gg/plandex-ai
- type: Twitter
url: https://twitter.com/plandex_ai
- type: YouTube
url: https://www.youtube.com/@plandex-ai
- type: Discussions
url: https://github.com/plandex-ai/plandex/discussions
- type: Issues
url: https://github.com/plandex-ai/plandex/issues
- type: Docker
url: https://hub.docker.com/r/plandexai/plandex-server
- type: DockerCompose
url: https://github.com/plandex-ai/plandex/blob/main/app/docker-compose.yml
- type: SpectralRules
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/rules/plandex-rules.yml
- type: Vocabulary
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/vocabulary/plandex-vocabulary.yml
- type: JSON-LD
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/json-ld/plandex-context.jsonld
- type: NaftikoCapability
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/capabilities/plandex-plan-management.yaml
- type: NaftikoCapability
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/capabilities/plandex-context-and-diffs.yaml
- type: Plans
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/plans/plandex-plans-pricing.yml
- type: RateLimits
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/rate-limits/plandex-rate-limits.yml
- type: FinOps
url: https://raw.githubusercontent.com/api-evangelist/plandex/main/finops/plandex-finops.yml
- type: Features
data:
- name: 2M-Token Effective Context Window
description: Smart context management loads only what's needed per step, enabling reliable work in large projects and files.
- name: Tree-Sitter Project Maps
description: Fast project map generation and syntax validation across 30+ programming languages. Indexes directories with 20M+ tokens.
- name: Cumulative Diff Sandbox
description: AI-generated changes are isolated from project files until explicitly applied, with cumulative review and roll-back.
- name: Configurable Autonomy
description: Five autonomy levels — None, Basic, Plus, Semi-Auto, Full-Auto — selectable per-plan or via CLI flags.
- name: Automated Debugging
description: Repeatedly runs commands (builds, tests, lints, scripts) and auto-fixes failures with rollback. Also debugs browser apps via Chrome.
- name: Model Packs
description: Curated combinations of models bound to internal roles (planner, coder, builder, summarizer, verifier, context loader); built-in packs for daily, reasoning, strong, cheap, oss, and planner-specialized variants.
- name: Multi-Provider Support
description: First-class support for Anthropic, OpenAI, Google AI Studio, Google Vertex AI, Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, OpenRouter, Ollama, and any OpenAI-compatible custom provider.
- name: Claude Pro/Max Subscription
description: Plandex can use a Claude Pro or Max subscription as the credential when calling Anthropic models.
- name: Context Caching
description: Built-in context caching across OpenAI, Anthropic, and Google models reduces latency and cost on multi-step plans.
- name: Plan Version Control
description: Every plan update is versioned, with branching for exploring multiple paths or comparing different models. Rewind to any prior SHA.
- name: Git Integration
description: Commit message generation, optional auto-commits, and clean integration with project git history.
- name: REPL with Fuzzy Auto-Complete
description: "Interactive shell launched by `plandex` (or `pdx`) with fuzzy command and file completion; backslash equivalents (`\\new`, `\\tell`) for every command."
- name: One-Line Install
description: "Zero-dependency CLI install via `curl -sL https://plandex.ai/install.sh | bash`. Docker compose for the self-hosted server."
- name: Background Tasks
description: "`--bg` flag runs plans concurrently in the background under separate streams."
- name: Smart Context + Auto-Load Context
description: Loads only the files needed for each implementation step (smart-context) and uses the project map to choose them (auto-load-context).
- name: Streaming Plan Execution
description: tell, build, and connect endpoints stream model responses live; clients can reconnect to in-progress plans after disconnects.
- type: UseCases
data:
- name: Large Refactors
description: Coordinate refactors that touch dozens of files across a large codebase without losing the thread between steps.
- name: Polyglot Project Work
description: Work in repositories that span 30+ languages thanks to tree-sitter project maps.
- name: Adding Features To Real Projects
description: Take a feature from idea through chat mode, into a detailed implementation plan, into reviewed and applied file changes.
- name: Automated Debugging
description: Wrap a flaky build, test, or browser app in `plandex debug` and let Plandex iteratively repair it.
- name: Codebase Onboarding And Q&A
description: Use chat mode and the project map to ask questions about an unfamiliar codebase.
- name: Multi-Model Comparisons
description: Branch a plan to run different model packs against the same context and compare results.
- name: Long-Running Background Coding
description: Kick off `--bg` plans, switch repos, and reconnect to streaming output later.
- name: BYO Subscription Coding Agent
description: Use a Claude Pro/Max subscription as the credential for an autonomous coding agent.
- name: Self-Hosted AI Coding For Sensitive Codebases
description: Run the Plandex server in Docker on-prem with locally-hosted Ollama models or a private custom provider.
- type: Integrations
data:
- name: Anthropic Claude
description: Direct Anthropic API integration; also supports Claude Pro/Max subscriptions.
- name: OpenAI
description: Direct OpenAI API integration via OPENAI_API_KEY.
- name: OpenRouter.ai
description: Default recommended provider for self-hosted Plandex; also used as a failover route across other configured providers.
- name: Google AI Studio
description: Gemini models via GEMINI_API_KEY.
- name: Google Vertex AI
description: Gemini and Anthropic models via Vertex AI credentials.
- name: Microsoft Azure OpenAI
description: OpenAI models on Azure with deployment-name mapping.
- name: AWS Bedrock
description: Anthropic models on Bedrock with AWS profile or env-var credentials.
- name: DeepSeek
description: DeepSeek models via DEEPSEEK_API_KEY.
- name: Perplexity
description: Perplexity models via PERPLEXITY_API_KEY.
- name: Ollama
description: Local model hosting via Ollama; no API keys required.
- name: Custom Providers
description: Any OpenAI-compatible API can be added via a JSON config (`plandex models custom`).
- name: Relace
description: Instant-apply fallback model used when Plandex cannot apply edits deterministically (Plandex Cloud).
- name: Git
description: Branching, commit-message generation, optional auto-commits.
- name: Chrome
description: Automated debugging of browser applications when Chrome is installed.
- name: Docker
description: Self-hosted server distributed as a Docker image with a published docker-compose stack.
- name: Postgres
description: Backing database for the Plandex server.
- name: LiteLLM Proxy
description: Embedded LiteLLM proxy used by the server to talk to model providers uniformly.
- name: Stripe
description: Payment processing for Plandex Cloud subscriptions and credit purchases.
- name: Loops
description: Email marketing for Plandex updates (Plandex Cloud).
- name: Google Analytics
description: Basic usage analytics (Plandex Cloud).
- name: Rollbar
description: Error tracking (Plandex Cloud).
- type: Solutions
data:
- name: Self-Hosted / Local Mode
description: Run Plandex locally with Docker and BYO model-provider keys. MIT-licensed and free.
- name: Plandex Cloud — BYO API Key Mode (Historical)
description: Hosted Plandex with user-supplied provider keys, $30/month after trial. Winding down 2025-10-03.
- name: Plandex Cloud — Integrated Models Mode (Historical)
description: Hosted Plandex with integrated credit billing, $45/month including $20/mo of non-expiring credits. Winding down 2025-10-03.
maintainers:
- FN: Kin Lane
email: [email protected]