Aider (harness)
OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.
At a glance
- Type
- Terminal-native AI pair programmer (OSS, Python)
- Tier
- T2
- Section
- Agent IDEs & coding harnesses
- Created
- 2023-05
- Latest release
- aider 0.x rolling (2025-2026)
- License
- Apache-2.0
- GitHub
- ~28k★, Python
- Pricing
- Free (OSS); usage via LLM provider
- Funding
- OSS — no commercial entity
Taxonomy
- storage
- file
- retrieval
- injection
- persistence
- cross-session
- update
- user-edit
- unit
- document
- governance
- inspectable
- conflict
- human-arbitrate
When to use
Optimised for: Architect/Editor split + repo-map context + multi-model via LiteLLM
Anti-fit: CLI-only; no GUI; primarily text editing — limited tool execution vs Claude Code
Pros & cons
Pros
Earliest-mover credibility; multi-model is real — switching from Claude to GPT to Gemini is a one-line config change; Aider edit-benchmark is widely cited.
Cons
Small dev team; trails newer agents on tool-use surface; weaker MCP ecosystem than Claude/Codex CLI.
Claims & capabilities
~28k★; among the earliest production-quality terminal coding agents; multi-model (Anthropic, OpenAI, Gemini, Ollama via LiteLLM).
Technical surface
- API surface
- CLI (Python)
- Backend storage
- local repo + CONVENTIONS.md
- Deployment
- Self-host (pip install aider-chat)
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- single-user (CLI)
- MCP
- depth-floor — Aider primarily uses its own tool-call format; MCP support tracked in issues
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other agent ides & coding harnesses in the catalog, ranked by inbound references.
- Bedrock AgentCore (AWS) T2
AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).
- Claude Code (Anthropic) T1
Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.
- GitHub Copilot (Agent Mode) T1
The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.
- Amazon Q Developer T1
Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.
- Anthropic Computer Use T1
Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.
- Bolt.new (StackBlitz) — harness T1
Cross-listing of Bolt.new at the harness layer. StackBlitz's WebContainer technology runs full Node.js in-browser; Bolt prompts the user for an app spec, then writes/edits/runs/deploys it entirely in-browser. The Coding-agent-memory row remains canonical for the memory framing.
Related systems
References (1)
- LiteLLM depends on at runtime — po-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited mark