Minimal Go autonomous agent runtime — 5 deps, ~11 MB, instant startup.

One binary. One loop. Zero frameworks. ReAct (Reasoning + Acting) — think, therefore act.

# Install
go install github.com/BackendStack21/kode/cmd/odek@latest

# Use (set ODEK_API_KEY, DEEPSEEK_API_KEY, or OPENAI_API_KEY)
export ODEK_API_KEY=sk-...
odek run "How many lines in go.mod?"
# → 3 lines

odek is not a framework. It's a runtime — the smallest possible surface area between an LLM and your tools.

odek run --sandbox — every session spawns an isolated Docker container. No network, no host mounts beyond the working directory, zero capabilities, destroyed on exit. --ctx files are automatically injected into the container at /workspace/. Full security model in docs/SANDBOXING.md.

Parallel OS-process sub-agents via delegate_tasks. True isolation — each sub-agent is a fresh odek subagent process with its own config, tools, and termination timeout. Up to 8 concurrent workers. docs/SUBAGENTS.md

Skill-matched SKILL.md files load on-demand. Auto-learns from patterns every session — detects multi-step procedures, error recoveries, repeated actions, and user corrections. LLM-enhanced: each detected pattern is enriched with an LLM-generated name, description, trigger keywords, and structured body with overview, steps, pitfalls, and verification sections. Use --no-learn to disable. Import skills from any URI with automatic LLM risk assessment. docs/CLI.md#skills

Three tiers: facts (agent-managed durable entries), session buffer (auto-appended turn summaries), episodes (LLM-extracted knowledge from past sessions). Merge-on-write via go-vector RandomProjections — cosine >0.7 auto-merges, <0.3 auto-adds. Saves ~80% LLM calls. docs/MEMORY.md

Save, resume, list, trim, and clean up conversations. Sessions persist as JSON in ~/.odek/sessions/. Continue any session with odek continue. docs/SESSIONS.md

Four-layer priority chain: global (~/.odek/config.json) → project (./odek.json) → ODEK_* env vars → CLI flags. ${VAR} substitution in config files. docs/CONFIG.md

Any OpenAI-compatible endpoint: Deepseek, OpenAI, Anthropic, Ollama, vLLM, Groq, Together, Fireworks — anything that speaks /chat/completions. Per-model profiles for thinking depth and context windows. docs/PROVIDERS.md

odek serve — browser-based agent with @ resource completion (@file.go, @sess:abc123), drag-and-drop file attachments, WebSocket streaming, and a full IDE-style console. docs/WEBUI.md

Run agent tasks directly from Telegram via long-polling. Supports slash commands (/plan, /sessions, /resume, /prune, /help, etc.), voice message transcription, photo analysis, conversation persistence across restarts, saved plan files, and daily token budgeting. No external Telegram libraries — built on stdlib net/http. docs/TELEGRAM.md

Attach files to any prompt with --ctx / -c (CLI), @filename inline references (CLI + REPL + Web UI), or drag-and-drop (Web UI). File content is injected as context blocks before the task — no tool calls needed. Comma-separate multiple files: --ctx main.go,lib.go. docs/CLI.md#file-attachments

Server (odek mcp) — expose odek's native tools (shell, read/write/search files, patch, browser) to Claude Code, Cursor, and any MCP client. Client (mcp_servers config) — odek connects to external MCP servers (Playwright, Fetch, GitHub, SQLite, etc.) and makes their tools available to the agent as <server>__<tool>. Both directions in one binary. docs/MCP.md

Built-in read_file, write_file, search_files, patch, shell, and browser tools. All gated by a unified security layer (dangerous config) — classify operations as allow / deny / prompt per risk class. No third-party dependencies. docs/SECURITY.md

# Single-shot task
odek run "List the files"

# With session persistence
odek run --session "Refactor auth module"
odek continue "Add rate limiting"

# Sandboxed (Docker isolation)
odek run --sandbox "npm audit"

# Different model
odek run --model gpt-4o --base-url https://api.openai.com/v1 "Explain this"

# With skill learning (on by default — use --no-learn to disable)
odek run "Set up a Go project with CI"

# Interactive REPL
odek repl

# Attach files for context
odek run --ctx data.csv "analyze this"
odek run --ctx main.go,lib.go "compare these files"
odek run "@README.md what does this project do?"

import "github.com/BackendStack21/kode"

agent, err := odek.New(odek.Config{
    Model:          "deepseek-chat",
    APIKey:         os.Getenv("ODEK_API_KEY"),
    MaxIterations:  30,
    Tools:          []odek.Tool{&myCustomTool{}},
    SystemMessage:  "You are an expert at refactoring Go code.",
})
defer agent.Close()

result, err := agent.Run(context.Background(), "Refactor this module")

The full Config struct supports: BaseURL, Thinking, SandboxCleanup, Renderer, MemoryConfig, MemoryDir, Skills, SkillManager, and NoProjectFile.

go test ./...                  # 1760+ tests, all pass (no setup required)
go test -race ./...           # race detector clean
go test -cover ./...          # overall coverage ~85%

Everything runs with go test — no Docker, no network, no external services required for unit tests.

Coverage highlights: internal/tool 100%, internal/llm 87.9%, internal/loop 89.4%, internal/session 89.7%, internal/telegram 86.9%, internal/memory 86.2%, internal/skills 86.3%.

MIT