kodara 0.3.0

Memory Layer for AI Development — Architecture-aware context engine

Kodara

Memory Layer for AI Development

Kodara converts your codebase into structured, queryable memory — so your AI assistant always has the right context, not the entire repository.

Without Kodara:  AI reads 44 files  →  41,160 tokens  →  $0.62/query
With Kodara:     AI reads 2 files   →   2,400 tokens  →  $0.04/query
                                                      ↑ 94% reduction

---

Quick Start

pip install kodara

cd your-project
kodara init          # index project → build memory
kodara ask "How does authentication work?"

No API keys. No configuration. Works with any AI tool.

After kodara init you'll see your token savings estimate immediately.

---

Commands

The differentiator between plans is project size and cloud infrastructure — not command availability on lower tiers.

FREE — all users (up to 200 files)

Command	What it does
kodara init	Scan project, build dependency graph, create .kodara/ memory
kodara ask "<query>"	Get relevant context for your AI assistant
kodara status	Current index status
kodara watch	Live auto-update as files change
kodara stats	Token savings and cost report
kodara history <file>	Git evolution: commits, authors, change frequency
kodara note add <file> "<text>"	Annotate a file with context
kodara snapshot	Save current project memory state
kodara install-hook	Git post-commit auto-update hook
kodara repos list	List all indexed projects

PRO — $19/month · everything in Free + unlimited files + cloud

Command	What it does
kodara impact <file>	Which modules break if you change this file?
kodara context	Generate ARCHITECTURE.md
kodara review	Analyze uncommitted changes + impact
kodara diff <base>	Impact analysis vs a branch or commit
kodara why <file>	WHY this file exists (git + notes + AI explanation)
kodara simulate-change <file>	Risk score + downstream cost + AI narrative
kodara heatmap	Responsibility heatmap
kodara dna	Architectural fingerprint — detect patterns
kodara learn	Save DNA snapshot
kodara evolve	DNA history over time
kodara compare <p1> <p2>	Compare two project architectures
kodara drift	Detect architectural drift since last snapshot
kodara clone-pattern <url> --into <dir>	Clone architectural structure from any repo
kodara scan <url>	Scan any GitHub repo
kodara mcp	MCP server — Cursor/Claude get context automatically
kodara backup	Upload .kodara/ to cloud
kodara restore	Download backup
kodara login	Authenticate with email OTP

TEAM — $25/user/month · everything in Pro + shared memory

Command	What it does
kodara onboard	Reading guide for new developers
kodara bus-factor	Files only one person knows — single point of failure
kodara debt	Technical debt heatmap
kodara arch-init	Auto-detect architecture layers
kodara check-architecture	Validate layer rules, show violations
kodara team cloud-create <name>	Create shared team memory
kodara team cloud-join <code>	Join team with invite code
kodara team cloud-push	Sync memory to team
kodara team cloud-pull	Pull team memory

ENTERPRISE — custom annual contract · everything in Team

Command	What it does
kodara ci-check	Exit 1 on violations — for CI/CD pipelines
kodara init-ci	Create .github/workflows/kodara.yml

Plus: SSO/SAML, on-premise deployment, SLA, dedicated support.

---

Real Performance Numbers

Tested on a 44-file Python project (Kodara itself):

Query	Without	With Kodara	Reduction
"How does the context engine work?"	41,160 tok	2,378 tok	94.2%
"Where is semantic search?"	41,160 tok	2,776 tok	93.3%
"How are stats tracked?"	41,160 tok	1,138 tok	97.2%
"How does git history work?"	41,160 tok	1,713 tok	95.8%
"How does impact analysis work?"	41,160 tok	4,291 tok	89.6%

Average: 94% token reduction

Methodology: "without" = full codebase read. "with" = module metadata + 2 most relevant files. Pricing: $15/1M tokens (GPT-4o / Claude Opus input).

Cost at Scale

Usage	Per developer/month	Per developer/year
Light (20 queries/day)	save $255	save $3,065
Medium (50 queries/day)	save $638	save $7,663
Heavy (100 queries/day)	save $1,277	save $15,326

Team size	Monthly savings	Annual savings
5 devs	$3,192	$38,314
10 devs	$6,385	$76,628
50 devs	$31,928	$383,138

---

How It Works

kodara init
    │
    ├── Scans all source files (Python, JS/TS, Go, Rust, Java, C/C++, Ruby, PHP)
    ├── Extracts: classes, functions, imports, exports via AST
    ├── Builds dependency graph (NetworkX DiGraph)
    ├── Generates semantic summaries per module
    ├── Collects git history (commit frequency, authors, change hotspots)
    └── Saves to .kodara/index.json (project-local, git-ignorable)

kodara ask "How does X work?"
    │
    ├── Tokenizes + stems query
    ├── IDF-weighted keyword scoring across all modules
    ├── Graph expansion: pulls in direct dependencies
    ├── Returns: top N modules + their relationships
    └── Surfaces any developer notes (kodara note) for those files

---

Installation

# Free (no API keys needed)
pip install kodara

# With AI explanations for why/simulate-change (uses GitHub Models)
pip install "kodara[llm]"   # set GITHUB_TOKEN env var

# Pro features (MCP server, cloud backup, team memory)
pip install "kodara[pro]"

# Everything
pip install "kodara[all]"

Requires Python 3.10+. Works on macOS, Linux, Windows.

---

Plans

Free — $0 forever

All core commands. Up to 200 files per project. Local storage only.

pip install kodara

Pro — $19/month

Unlimited project size. Full analysis suite. Cloud backup. MCP integration. Saves $147–$295/month on average. ROI from day one.

pip install "kodara[pro]"

Team — $25/user/month

Everything in Pro. Shared memory — one developer indexes once, whole team benefits. 10 devs → saves $6,385/month on AI tokens. Coming soon at getkodara.dev.

Enterprise — Custom

Everything in Team. SSO/SAML, on-premise deployment, SLA, dedicated support. Contact us at getkodara.dev.

---

Storage

Everything lives in .kodara/ inside your project:

.kodara/
  index.json       # module graph + summaries
  stats.json       # token savings history
  notes.json       # developer annotations
  snapshots/       # periodic memory captures
    2024-01-15_143022.json

Add .kodara/ to .gitignore or commit it — your choice.

---

Example Output

$ kodara ask "How does payment processing work?"

Context for: "How does payment processing work?"
Found 6 relevant modules (1,840 tokens)

  billing/processor.py      ★★★★★  PaymentProcessor, process_charge()
  billing/stripe_client.py  ★★★★   StripeClient, create_intent()
  billing/models.py         ★★★    Payment, Refund, Invoice
  api/billing_routes.py     ★★★    POST /pay, POST /refund
  config/payments.py        ★★     Stripe keys, retry config
  utils/currency.py         ★★     format_amount(), convert()

  Dependency chain: api/billing_routes → billing/processor → billing/stripe_client

$ kodara impact billing/processor.py

Impact Analysis: billing/processor.py
Risk: HIGH

  Direct (2):   api/billing_routes.py, workers/charge_worker.py
  Indirect (4): api/webhooks.py, reports/revenue.py, ...

$ kodara stats

Token savings — all time
  Queries: 47   Tokens saved: 1,823,040   Money saved: $27.35

---

License

MIT for personal and open-source use. Commercial use (Pro/Team/Enterprise) — see getkodara.dev.