Taste – Zero-config session-taste packer for AI agents

Taste, a zero-configuration tool for AI agents, compresses context from 56K to 1.9K tokens by automatically learning coding patterns from git history and session logs, enabling agents to write project-specific code with 97% less token usage.

Zero-config. Auto-learns. Just works. 97% smaller context · Auto-learns your style · Works with any agent Compresses AI agent context from 56K tokens to 1.9K tokens. Learns your coding patterns from git history and session logs. Results vary by project size and session history. You know the problem. You start an AI agent session. It reads your entire project: session logs, git diffs, READMEs, config files. It writes code that doesn't match your style. It wastes tokens and produces generic, bloated code. taste puts a stop to that. It learns your patterns. It compresses your context. It makes your agents write code like you do. You ask for a rate limiter. Your agent reads 56K tokens of context, installs a library, writes a generic implementation, and asks about your Redis setup. With taste: taste Creates .session-doc.md with 1.9K tokens Agent reads your patterns, writes code your way More examples in examples/ /dvcoolarun/taste-ai/blob/main/examples . Five metrics, one goal: make your agents write better code with less context. | Metric | Without taste | With taste | Improvement | |---|---|---|---| | Token usage | 56,000 | 1,950 | 97% reduction | | Context quality | Generic | Project-specific | Better | | Pattern learning | Manual | Automatic | Zero-config | | Agent support | Single | Multiple | 3+ agents | | Setup time | Hours | Seconds | Instant | 97% smaller context, auto-learns your style, and works with any agent. Every pattern taste learns is marked in the code with confidence scores. Reproduce it yourself: run taste learn in any project. Method and raw numbers: benchmarks/ /dvcoolarun/taste-ai/blob/main/benchmarks . Real-world examples: examples/ /dvcoolarun/taste-ai/blob/main/examples . That is the byproduct, not the pitch. These are average numbers, and they vary by project. Larger projects with more session history see better compression. Smaller projects with less history see smaller savings. And all of this is iterative: each time you run taste learn , it learns more patterns, which makes the next compression better. The rule was never "fewest tokens." It is: learn only what the project needs, and never skip validation, error handling, security, or accessibility. The context ends up small because it is necessary, not trimmed, and that is the part that stays useful. Better code quality is a side effect of learning your style, and that is the part that matters. Before compressing context, taste learns your patterns: 1. Collect session data → git diffs, session logs, taste config 2. Create summary → compact format, essential information only 3. Analyze with agent → calls opencode or claude 4. Extract patterns → naming, architecture, imports, error handling, style 5. Update taste config → append to TASTE.md, update .agent-taste.json Lazy, not negligent: validation, error handling, security, and accessibility patterns are never skipped. The most effort taste will ever ask of you: curl -fsSL https://raw.githubusercontent.com/dvcoolarun/taste-ai/main/install.sh | bash git clone https://github.com/dvcoolarun/taste-ai.git cd taste-ai chmod +x taste cp taste ~/.local/bin/ taste help That was it. It would be proud. It won't say it. In any project directory taste Generates .session-doc.md with compressed context Analyze last 3 sessions and learn patterns taste learn Analyze last 5 sessions taste learn --depth 5 Show patterns without updating files taste learn --dry-run Create default .agent-taste.json taste init Display current taste configuration taste show | Command | What it does | |---|---| taste | Pack session context into .session-doc.md | taste pack file | Pack to specific output file | taste init | Create default .agent-taste.json | taste show | Show current taste config | taste learn | Learn patterns from recent sessions agent-assisted | taste help | Show help | taste learn analyzes your coding sessions and extracts patterns: ┌─────────────────────────────────────────────────────────┐ │ Data Collection │ │ - Last 3-5 session logs │ │ - Last 3-5 prompt logs │ │ - Git diffs last 3-5 commits │ │ - Current taste config │ └─────────────────────────────────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────────────────────┐ │ Summary Creation │ │ - Compact format 18KB typical │ │ - Token-efficient structure │ │ - Essential information only │ └─────────────────────────────────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────────────────────┐ │ Agent Analysis │ │ - Calls opencode or claude │ │ - Uses pattern extraction prompt │ │ - Returns structured patterns │ └─────────────────────────────────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────────────────────┐ │ Pattern Extraction │ │ - NAMING conventions → TASTE.md │ │ - ARCHITECTURE patterns → TASTE.md │ │ - IMPORTS style → TASTE.md │ │ - ERROR HANDLING patterns → TASTE.md │ │ - STYLE preferences → TASTE.md │ │ - BANNED PATTERNS → .agent-taste.json │ └─────────────────────────────────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────────────────────┐ │ Auto-Update │ │ - Positive patterns → TASTE.md │ │ - Banned patterns → .agent-taste.json │ │ - Preserve existing patterns │ │ - Avoid duplicates │ └─────────────────────────────────────────────────────────┘ | Category | What It Learns | Output Location | |---|---|---| | NAMING | Function naming conventions snake case, camelCase, etc. | TASTE.md | | ARCHITECTURE | Project structure patterns, dependency management | TASTE.md | | IMPORTS | Import style, ordering, lazy vs eager imports | TASTE.md | | ERROR HANDLING | Try/catch patterns, error propagation | TASTE.md | | STYLE | Code formatting, function length, comments | TASTE.md | | BANNED PATTERNS | What NOT to do, with reasons | .agent-taste.json | taste learns both positive patterns what to do and negative patterns what NOT to do . Banned patterns are extracted from user corrections, past mistakes, and feedback. Example banned patterns: { "banned patterns": "--single-process Chromium flag on macOS reason: causes crashes, documented failure ", "hardcoding connection URLs or env specific values reason: caused 'Queue service unavailable' failure ", "jumping to implementation before design alignment reason: wasted work when pricing model wasn't confirmed ", "removing comments during code rewrites reason: user explicitly called out and expects preservation ", "using browser only Node APIs in subprocess reason: ErrorEvent caused ReferenceError " } Why banned patterns matter: Specific - Not generic "don't use classes" but concrete "don't use --single process Chrome flag" Actionable - Clear reasons that explain WHY it's banned Learned from mistakes - "was replaced with page.setContent" shows historical context Platform-aware - "crashes on macOS" shows environment-specific knowledge How banned patterns work: - Agent extracts BANNED PATTERNS from session data - Patterns are written to .agent-taste.json as a JSON array - When you run taste , banned patterns are included in .session-doc.md - Agents read the banned patterns and avoid those patterns Each pattern includes a confidence score 0-1 : 0.9-1.0 : Very high confidence seen multiple times 0.8-0.9 : High confidence seen consistently 0.7-0.8 : Medium confidence seen occasionally 0.6-0.7 : Low confidence seen once or twice <0.6 : Not included insufficient evidence Each time you run taste learn , it: Reads your latest session logs and git diffs Analyzes patterns with an AI agent Extracts structured patterns with confidence scores Updates your taste config TASTE.md, .agent-taste.json Preserves existing patterns and avoids duplicates The more you use taste, the better it learns your style. Pattern confidence increases as it sees the same patterns across multiple sessions. Before starting opencode taste Feed to opencode opencode . Before starting claude taste Feed to claude claude . Generate context taste Agent reads .session-doc.md automatically TASTE BOUNDARIES Source: .agent-taste.json json { "flavor": "Functional TypeScript, strict types, zero dependencies", "banned patterns": "classes", "any", "console.log" , "style": "Implicit returns, max 20 lines per function" } Branch: main Last 5 commits: abc1234 refactor: extract auth to /core def5678 feat: add token validation Changed files last commit : src/auth.ts | 12 +++--- src/utils.ts | 5 +++- taste learn Output taste: Analyzing last 3 sessions... taste: Collecting session data... taste: Summary created: 18818 bytes taste: Calling opencode for analysis... LEARNED PATTERNS last 3 sessions : NAMING: - functions describe action verbs confidence: 0.9 - classes use PascalCase Prefixed confidence: 0.9 - variables underscore separated snake case confidence: 0.8 ARCHITECTURE: - Python FastAPI fronts with Node subprocess backend via stdin stdout bridge - async job queue with redis backend and RQ worker - dual storage PDF disk and Redis cache IMPORTS: - lazy import inside endpoint to avoid side effects - from stdlib then third party then local grouped - explicit imports not star imports used ERROR HANDLING: - log then raise precise HTTPException with detail - check rate limit before database operation - refund credits by saving values before session closes STYLE: - short direct corrections fix agent behavior precisely - comment preservation expected across rewrites BANNED PATTERNS: - --single-process Chromium flag on macOS reason: causes crashes, documented failure - hardcoding connection URLs or env specific values reason: caused 'Queue service unavailable' failure - jumping to implementation before design alignment reason: wasted work when pricing model wasn't confirmed - removing comments during code rewrites reason: user explicitly called out and expects preservation - using browser only Node APIs in subprocess reason: ErrorEvent caused ReferenceError Updated: TASTE.md, .agent-taste.json Auto-Capture taste learn automatically captures your current session if no recent session files exist: bash If docs/session- .md doesn't exist or is older than 2 hours taste learn It will: 1. Capture git history + diffs 2. Capture current taste config 3. Create docs/session- YYYY-MM-DD-HHMM .md 4. Create prompts/prompt- YYYY-MM-DD-HHMM .md 5. Analyze patterns and update taste config What it captures: - Git history last 3 commits + diffs - Current taste config .agent-taste.json or TASTE.md - Last 3-5 session log summaries What it does NOT capture: - Terminal histories - Agent session logs - Full file contents Before taste: Raw context: - Session logs: ~40,000 words - Git diffs: ~10,000 words - README.md: ~1,000 words - Session notes: ~500 words Total: ~51,000 words ~66,000 tokens After taste: Compressed context: - Taste config: ~120 words - Git summary: ~200 words - Session notes: ~200 words - Agent config: ~500 words Total: ~1,500 words ~1,950 tokens Savings: Words : 51,000 → 1,500 97% reduction Tokens : 66,000 → 1,950 97% reduction Create ~/.config/taste/base.json for global settings: { "flavor": "Standard idiomatic development", "banned patterns": , "style": "Prefer clarity over brevity" } Create .agent-taste.json in your project root: { "flavor": "Functional TypeScript, strict types, zero dependencies", "banned patterns": "classes", "any", "console.log" , "style": "Implicit returns, max 20 lines per function" } After running taste learn, banned patterns are automatically populated: { "flavor": "Standard idiomatic development", "banned patterns": "--single-process Chromium flag on macOS reason: causes crashes, documented failure ", "hardcoding connection URLs or env specific values reason: caused 'Queue service unavailable' failure ", "jumping to implementation before design alignment reason: wasted work when pricing model wasn't confirmed ", "removing comments during code rewrites reason: user explicitly called out and expects preservation ", "using browser only Node APIs in subprocess reason: ErrorEvent caused ReferenceError " , "style": "Prefer clarity over brevity", "learned": {} } Does it need a config file? No. An optional .agent-taste.json or TASTE.md can be created, but nothing is required. taste works with zero configuration. What if I really need that 120-line cache class? You don't. Insist anyway and taste will learn your pattern. Slowly. Correctly. While looking at you. Does it scale? The context you never waste scales infinitely. Zero tokens wasted, zero generic code, 100% style matching since forever. Why "taste"? You know exactly why. - bash 4.0+ - git - opencode or claude for taste learn - Multi-agent support claude, codex, commandcode - Session auto-capture daemon mode - Global taste config ~/.config/taste/ - JSON output for agents - Integration with more agent harnesses Contributions are welcome Please feel free to submit a Pull Request. - Fork the repository - Create your feature branch git checkout -b feature/amazing-feature - Commit your changes git commit -m 'Add amazing feature' - Push to the branch git push origin feature/amazing-feature - Open a Pull Request MIT /dvcoolarun/taste-ai/blob/main/LICENSE . The shortest license that works.