Coda

Coda is a code companion that lives in Slack. Coding agents help us write code faster, but most engineering work is understanding how things work, reviewing PRs, figuring out what broke and why, triaging the backlog, and deciding what’s safe to change. That work happens in Slack and GitHub, not in an editor. Coda fills that gap. It answers architecture questions like “how does auth work” or “where is the model API call”. It reviews PRs and open branches, diffs them against your conventions, and leaves comments. It reads open issues and flags the urgent ones worth tackling next. And it does all of this in Slack, alongside your team. The code is public at agno-agi/coda.

How it works

Coda is a team of up to five specialist agents coordinated by a leader:

Agent	Role
Explorer	Searches local code without modifying it, answers architecture questions, and can post GitHub review or issue comments
Coder	Writes code in isolated worktrees, opens PRs
Planner	Breaks features into ordered GitHub issues
Triager	Labels, comments on, and closes issues based on code analysis
Researcher	Searches the web for docs, APIs, and error messages when `PARALLEL_API_KEY` is set

Coda’s instructions direct the Coder to use git worktrees on coda/* branches and open pull requests for review. The repo-sync task updates each configured main checkout. CodingTools also exposes shell and git access, so branch protections remain the enforcement point for protected branches and human review. Coda runs in your infrastructure and calls the services you configure. Model prompts go to the model provider. Repository operations, diffs, and comments use GitHub. Messages and digests use Slack. The optional Researcher sends research queries to Parallel. Between them, the agents cover:

Capability	What it does
Architecture Q&A	Answers “how does auth work” with file paths and line numbers
PR reviews	Pulls the diff, checks it against your conventions, leaves inline comments
Issue triage	Categorizes, labels, flags duplicates, closes junk
Planning	Turns a feature request into ordered, well-scoped GitHub issues
Web research	Brings back framework docs, library APIs, and error explanations with sources
Code writing	Ships changes from isolated worktrees as PRs

Scheduled tasks

Coda also shows up on its own. Two background tasks register at startup:

Task	What it does
Daily digest	Posts a morning summary: what merged, what needs review, what went stale
Repo sync	Pulls the latest changes from configured repos every 5 minutes

Repo sync always runs. The daily digest only registers when both DIGEST_CHANNEL and SLACK_TOKEN are set in .env. Set DIGEST_CHANNEL to the Slack channel ID the summary should post to (right-click a channel in Slack, then View details to copy the ID).

Self-learning

Coda can record coding standards, conventions, and patterns for later retrieval. The learning tools come from Agno’s Learning Machines:

Week 1	Week 4
Writes working code using generic patterns	Follows your service layer conventions, uses your team’s error handling pattern, matches your naming style

Run locally

The Coda README walks through this in more detail.

git clone https://github.com/agno-agi/coda.git && cd coda

cp example.env .env
# Edit .env: add OPENAI_API_KEY and GITHUB_ACCESS_TOKEN

OPENAI_API_KEY comes from platform.openai.com. For GITHUB_ACCESS_TOKEN, create a fine-grained Personal Access Token with Contents (read and write), Pull requests (read and write), Issues (read and write), and Metadata (read). The full walkthrough is in docs/GITHUB_ACCESS.md. PARALLEL_API_KEY (from parallel.ai) is optional; it enables the Researcher agent. Without it the team runs with no web research. Tell Coda which repos to learn by editing repos.yaml:

repos:
  - url: https://github.com/your-org/your-repo
    branch: main

The agno repo makes a good starting point, so you have some test questions to play around with. Then start Coda (Docker needs to be running):

docker compose up -d --build

Confirm it’s up at localhost:8000/docs.

Connect to the AgentOS UI

Open os.agno.com and sign in.
Click Connect OS → Local and enter http://localhost:8000.

This gives you a web UI to chat with Coda directly, plus sessions, traces, metrics, memory, and evaluations.

Deploy to Railway

You’ll need the Railway CLI installed and railway login completed.

# First-time setup (creates project, database)
./scripts/railway_up.sh

# Sync env vars after changing .env (handles multiline keys like PEM)
./scripts/railway_env.sh

# Redeploy after code changes
./scripts/railway_redeploy.sh

railway_up.sh provisions a pgvector database, creates the coda service with the variables from your .env, deploys, and creates a public domain. If .env has no JWT_VERIFICATION_KEY, the initial process exits after the domain is created. Copy that domain, generate the key below, sync it, and redeploy. The domain can take about 5 minutes; inspect startup with railway logs --service coda. See railway.json to adjust CPU, memory, and replica settings. Production runs with RBAC on (RUNTIME_ENV=prd is the default). Without JWT_VERIFICATION_KEY, the process exits during startup. After the key is configured, protected AgentOS routes require a valid token. The operational and documentation routes /, /health, /info, /docs, /redoc, /openapi.json, and /docs/oauth2-redirect remain public.

Open os.agno.com, click Connect OS → Live, and enter the Railway domain created by railway_up.sh.
Go to Settings and generate a key pair.
Add the public key to .env as JWT_VERIFICATION_KEY (paste the full PEM block).
Push it and redeploy:

./scripts/railway_env.sh
./scripts/railway_redeploy.sh

railway_env.sh handles multiline values, so the PEM key syncs correctly.

Connect to Slack

With Coda running, follow the Slack setup guide to create your Slack app, then add the credentials to .env:

SLACK_TOKEN="xoxb-***"
SLACK_SIGNING_SECRET="***"

Restart to pick up the credentials:

docker compose up -d

There are two ways to talk to Coda:

Where	How
Direct message	Find Coda under Apps in the Slack sidebar and message it directly
In a channel	Run `/invite @Coda`, then mention @Coda in any message

Each thread is its own conversation. Follow-ups in the same thread don’t need to @mention Coda again. If Coda is deployed, point your Slack app’s Event Subscriptions Request URL at https://<your-domain>/slack/events and wait for Slack to verify it.

Example prompts

Try these once your repos are configured:

@Coda where is the webhook handler for Stripe events?
@Coda review PR #42
@Coda triage the open issues and label them
@Coda plan out adding webhook support to the payments service
@Coda what changed in FastAPI 0.135?

Run evals

Five eval categories cover the team’s behavior:

Category	What it tests
security	Responses never leak keys, tokens, or credentials
routing	The leader delegates to the right specialist and tools
exploration	Answers point to the correct files and code
synthesis	Answers lead with the result, cite file paths, and suggest next steps
refusal	The team declines dangerous requests and asks for clarification on ambiguous ones

Evals call the real team, so set up a virtual environment and start the database first:

./scripts/venv_setup.sh && source .venv/bin/activate
docker compose up -d coda-db

python -m evals.run                      # All categories
python -m evals.run --category security  # One category
python -m evals.run --verbose            # Show response previews

Source

Coda is open source at agno-agi/coda. The in-repo docs cover GitHub access and Slack setup in detail.

Get Started

Starters

Apps

Agno CLI

How it works

Scheduled tasks

Self-learning

Run locally

Connect to the AgentOS UI

Deploy to Railway

Connect to Slack

Example prompts

Run evals

Source

​How it works

​Scheduled tasks

​Self-learning

​Run locally

​Connect to the AgentOS UI

​Deploy to Railway

​Connect to Slack

​Example prompts

​Run evals

​Source

How it works

Scheduled tasks

Self-learning

Run locally

Connect to the AgentOS UI

Deploy to Railway

Connect to Slack

Example prompts

Run evals

Source