Skip to main content

we also can't pronounce cecli

Project description

Why cecli?

cecli (probably pronounced like "Cecily", aka aider-ce) is a community-driven fork of the Aider AI pair programming tool. Aider is a fantastic piece of software with a wonderful community but it has been painfully slow in receiving updates in the quickly evolving AI tooling space.

We aim to foster an open, collaborative ecosystem where new features, experiments, and improvements can be developed and shared rapidly. We believe in genuine FOSS principles and actively welcome contributors of all skill levels.

If you are looking for bleeding-edge features or want to get your hands dirty with the internals of an AI coding agent, here's your sign. LLMs are a part of our lives from here on out so join us in learning about and crafting the future.

Links

Discord Chat 🞄 Changelog 🞄 Issue Queue

Documentation/Other Notes:

You can see a selection of the enhancements and updates by comparing the help output:

diff -uw --color <(aider --help) <(cecli --help)

Installation Instructions

This project can be installed using several methods:

Package Installation

pip install cecli-dev

or

uv pip install --native-tls cecli-dev

The package exports a cecli command that accepts all of Aider's configuration options

Tool Installation

uv tool install --native-tls --python python3.12 cecli-dev

Use the tool installation so aider doesn't interfere with your development environment

Configuration

The documentation above contains the full set of allowed configuration options but I highly recommend using an .cecli.conf.yml file. A good place to get started is:

model: <model of your choice>
agent: true
auto-commits: true
auto-save: true
auto-load: false
cache-prompts: true
check-update: true
debug: false
enable-context-compaction: true
context-compaction-max-tokens: 64000
env-file: .aider.env
show-model-warnings: true
use-enhanced-map: true
watch-files: false
tui: true

agent-config:
  large_file_token_threshold: 12500
  skip_cli_confirmations: false

mcp-servers:
  mcpServers:
    context7:
      transport: http
      url: https://mcp.context7.com/mcp

Use the adjacent .aider.env file to store model api keys as environment variables, e.g:

ANTHROPIC_API_KEY="..."
GEMINI_API_KEY="..."
OPENAI_API_KEY="..."
OPENROUTER_API_KEY="..."
DEEPSEEK_API_KEY="..."

Run Program

If you are in the directory with your .aider.conf.yml file, then simply running cecli or aider-ce will start the agent with your configuration. If you want additional sandboxing, we publish a docker container that can be ran as follows:

docker pull dustinwashington/aider-ce
docker run \
  -it \
  --user $(id -u):$(id -g) \
  --volume $(pwd):/app dustinwashington/aider-ce \
  --volume $(pwd)/.aider.conf.yml:/.aider.conf.yml \
  --volume $(pwd)/.aider.env:/.aider/.env \
  --config /app/.aider.conf.yml

This command will make sure all commands ran by the coding agent happen in context of the docker container to protect the host file system from any infamous agentic mishap

Project Roadmap/Goals

The current priorities are to improve core capabilities and user experience of the Aider project

  1. Base Asynchronicity (cecli coroutine-experiment branch)
  • Refactor codebase to have the main loop run asynchronously
  • Update test harness to work with new asynchronous methods
  1. Repo Map Accuracy - Discussion
  1. Context Discovery - Discussion
  • Develop AST-based search capabilities
  • Enhance file search with ripgrep integration
  • Implement RAG (Retrieval-Augmented Generation) for better code retrieval
  • Build an explicit workflow and local tooling for internal discovery mechanisms
  1. Context Delivery - Discussion
  • Use workflow for internal discovery to better target file snippets needed for specific tasks
  • Add support for partial files and code snippets in model completion messages
  1. TUI Experience - Discussion
  • Add a full TUI (probably using textual) to have a visual interface competitive with the other coding agent terminal programs
  • Re-integrate pretty output formatting
  • Implement a response area, a prompt area with current auto completion capabilities, and a helper area for managing utility commands
  1. Agent Mode - Discussion
  • Renaming "navigator mode" to "agent mode" for simplicity
  • Add an explicit "finished" internal tool
  • Add a configuration json setting for agent mode to specify allowed local tools to use, tool call limits, etc.
  • Add a RAG tool for the model to ask questions about the codebase
  • Make the system prompts more aggressive about removing unneeded files/content from the context
  • Add a plugin-like system for allowing agent mode to use user-defined tools in simple python files
  • Add a dynamic tool discovery tool to allow the system to have only the tools it needs in context

All Contributors (Both Cecli and Aider main)

@paul-gauthier @dwash96 @tekacs @ErichBSchulz
@ei-grad @joshuavial @chrisnestrud @chr15m
@johbo @fry69 @quinlanjager @caseymcc
@shladnik @jamwil @itlackey @tomjuggler
@szmania @vk4s @titusz @bphd
@daniel-vainsencher @1broseidon @akaihola @jalammar
@schpet @iamFIREcracker JV @KennyDizi
@ivanfioravanti @mdeweerd @itsmeknt @fahmad91
@cheahjs @youknow04 @pjcreath @pcamp
@miradnanali @o-nix Jonathan Ellis @codeofdusk
@claui @jpshackelford @Taik @Hambaobao
@therealmarv @muravvv @hypn4 @gmoz22
@contributor @ctoth @thehunmonkgroup @gcp
@sentienthouseplant @ktakayama @lreeves @nims11
@preynal @tgbender @apaz-cli Alexander Kjeldaas
@zhyu Yutaka Matsubara @burnettk @cryptekbits
@deansher @kennyfrc @lentil32 @malkoG
@mubashir1osmani @TimPut @zjy1412 @savioursho
@jayeshthk @susliko @FeepingCreature @misteral
@aelaguiz @DhirajBhakta @gopar @eltociear
@tao12345666333 @jpshack-at-palomar @smh @nhs000
@sannysanoff @ryanfreckleton @mbokinala @yamitzky
@mobyvb @ozapinq @nicolasperez19 @varchasgopalaswamy
@ffluk3 @tanavamsikrishna @tylersatre @pcgeek86
@tamirzb @taha-yassine @strayer @StevenTCramer
@Skountz @sestrella @rnevius @holoskii
@Netzvamp @peterhadlaw @pauldw @paulmaunders
@omri123 @MatthewZMD @mbailey @golergka
@matfat55 @mtofano @maledorak @mlang
@marcomayer @you-n-g wangboxue @rti
@prmbiy @omarcinkonis @Oct4Pie @mark-asymbl
@yazgoo michal.sliwa @mdklab @mario7421
liam.liu kwmiebach @kAIto47802 @jvmncs
@hydai @hstoklosa @gordonlukch @develmusa
@coredevorg @cantalupo555 @caetanominuzzo @yzx9
@zackees @wietsevenema @krewenki @vinnymac
@szepeviktor @lattwood @spdustin @henderkes
@daysm @devriesd @daniel-sc @damms005
@curran @cclauss @cjoach @csala
@bexelbie @branchv @bkowalik @h0x91b
@aroffe99 @banjo @anjor @andreypopp
@ivnvxd @andreakeesys @ameramayreh @a1ooha
@maliayas @akirak @adrianlzt @codefromthecrypt
@aweis89 @aj47 @noitcudni @solatis
@webkonstantin @khulnasoft-bot @KebobZ @acro5piano
@josx @joshvera @jklina @jkeys089
@johanvts Jim White @gengjiawen @jevon
@jesstelford @JeongJuhyeon @jackhallam @Mushoz
@zestysoft Henry Fraser @gwpl @garrett-hopper
@filiptrplan @FelixLisczyk @evnoj @erykwieliczko
@elohmeier @emmanuel-ferdman

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cecli_dev-0.95.7.tar.gz (1.6 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cecli_dev-0.95.7-py3-none-any.whl (658.2 kB view details)

Uploaded Python 3

File details

Details for the file cecli_dev-0.95.7.tar.gz.

File metadata

  • Download URL: cecli_dev-0.95.7.tar.gz
  • Upload date:
  • Size: 1.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for cecli_dev-0.95.7.tar.gz
Algorithm Hash digest
SHA256 011ff7121d2144efc6a864d5bdd53b7a27e160b3f5e9247e62a9098bc6551fb1
MD5 4fb29dc9b5c268af5ad939161d4a59e3
BLAKE2b-256 f137205870e9613930dc74875d4ea23bedcb7247e7f5a2044054844b1383fca8

See more details on using hashes here.

File details

Details for the file cecli_dev-0.95.7-py3-none-any.whl.

File metadata

  • Download URL: cecli_dev-0.95.7-py3-none-any.whl
  • Upload date:
  • Size: 658.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for cecli_dev-0.95.7-py3-none-any.whl
Algorithm Hash digest
SHA256 cd8fc6c733b35e8c6d909d7caa2a6bd5948ac058f6122dac792f48a7065995b2
MD5 61399f000b96ac8c03c20b555d2054b3
BLAKE2b-256 7022431362df4b11de75cf680c0d24d6347911d9f86f2ce9fe0b978463eca85d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page