________  ________                   _____
|\   __  \|\   __  \                 / __  \
\ \  \|\  \ \  \|\ /_  ____________ |\/_|\  \
 \ \  \\\  \ \   __  \|\____________\|/ \ \  \
  \ \  \\\  \ \  \|\  \|____________|    \ \  \
   \ \_______\ \_______\                  \ \__\
    \|_______|\|_______|                   \|__|

$ overbrilliant — the multi-agent CLI coding agent. completely free.

12,685 lines of TypeScript + Bun. Multi-agent orchestration with parallel sub-agents running across isolated worktrees, adaptive routing, and compute-matched eval — backed by FreeLLMAPI, which stacks 16+ providers' free tiers into one endpoint (~1.7B tokens/month, zero cost). Sign up with email, no credit card ever.

01

completely free — no API keys, no billing, no limits

OB-1 ships with FreeLLMAPI built in — a proxy that stacks 16+ LLM providers' free tiers into a single endpoint. ~1.7B tokens/month across the fleet, zero cost. Sign up with email, get a bearer token, start coding. No credit card ever.

  • FreeLLMAPI: a single URL that round-robins across Anthropic, OpenAI, OpenRouter, and 13+ other providers — whenever one throttles, the next picks up.
  • ~1.7B free tokens/month total across the federation. Enough for serious daily use, not just demos.
  • /models setup tab: live connection test with auto-model picker — picks the best free model available right now.
  • Bring your own key optionally: Full Anthropic, OpenAI, OpenRouter, and any OpenAI-compatible HTTP endpoint supported too.

02

multi-agent orchestration

A sub-agent runtime that spawns, isolates, and coordinates parallel workers. Fan-out N sub-agents across git worktrees, manage long-running tasks with stall detection, and keep token spend tight with an adaptive router that escalates only when Solo fails.

  • Worker runtime: each sub-agent gets its own LLM context, worktree copy, and token budget — mutations never collide.
  • Fusion: run N parallel candidates → auto-score with syntax/typecheck/compile → synthesize from the passers.
  • Council: author writes → reviewer critiques → revision loops → finalizer ships one clean answer.
  • Personas: casts a domain-specific expert panel → runs turn-based dialogue → facilitator distills consensus.
  • Adaptive router: runs Solo first, scores it against an objective check, escalates to Fusion/Council only on failure.
  • Long-running task management: TaskLedger + ProgressLedger track progress, detect stalls at 3 identical steps, and auto-replan (max 3 replans, max 20 rounds).
  • Token optimization: Solo@k math proves whether a heavy mode justifies its cost — if k cheap attempts at the same budget outperform, the router picks Solo.

03

gated agent loop

A ReAct cycle with per-action approval gates, streaming tokens, and auto-verification — everything Claude Code does, with read/write/bash/edit tools and plan/act modes.

  • Plan mode (read-only explores codebase first), Act mode (full read/write/bash/edit).
  • Per-action approval: ask / warn / deny gates based on a configurable policy.json file.
  • Auto-verification: after every file-changing turn, OB-1 runs your project's typecheck, test, lint — and fixes what fails.
  • Checkpointing with git worktrees: /rewind reverts to a known-good state. Zero lost work.

04

compute-matched eval — built-in honesty

No vague benchmarks — SWE-bench-shaped tasks with objective exit-0 checks. OB-1 proves each orchestration mode justifies its token cost against Solo@k.

  • Objective pass/fail: runs tasks in isolated worktrees, exit 0 = PASS. No model-as-judge ever.
  • Solo@k math: what would k plain attempts at the same token budget achieve? If advanced modes don't beat it, the answer is honest: just use Solo.
  • Per-mode runners (Solo, Fusion, Council, Personas) with parity reports rendering capability comparisons.

05

persistent memory engine

A SQLite-backed fact store you can actually inspect — facts, relationships, and reflections — all in one file. It remembers across sessions and injects relevant context just-in-time.

  • Plain-text facts with an immutable revision trail — Google Memory Bank model, never deletes, only appends.
  • Bi-temporal relationship graph: entities and typed edges that are invalidated (not destroyed) so history stays queryable.
  • Vector search via sqlite-vec (native KNN) with a zero-dep pure-TS cosine fallback — identical ranking either way.
  • Recency × importance × relevance scoring. Reflection engine synthesizes higher-level insights. Inspect at /memory.

06

repository intelligence

OB-1 builds a cross-reference graph of your codebase, ranks files by centrality, extracts symbols, and connects to language servers — so it knows your project before it touches a file.

  • Cross-ref graph + PageRank centrality — finds the files that actually matter in your repo.
  • Key symbol extraction via tree-sitter + LSP integration (diagnostics, go-to-definition).
  • Auto-generates a project index (AGENTS.md) with repo summary and conventions.
  • Git state tracking with branch analysis, worktree recovery and checkpointing.
  • Available as the repo_map tool and the /map slash-command.

07

safety sandbox

OS-level containment for shell commands, configurable permission policies, and destructive-command detection — so agents can't brick your machine.

  • macOS Seatbelt sandbox + Linux bubblewrap for all spawned processes.
  • Destructive command classifier: flags rm -rf, sudo, dd, mkfs with severity levels.
  • policy.json rules: allow, warn, or deny per-command-class, with a persistent trust store.

08

skills, MCP & TUI

On-demand markdown skills, a full MCP client, and a live React TUI — the full runtime surface of a serious dev agent.

  • Skills registry: lazy-loaded markdown instruction files the agent reads when first matched.
  • MCP client: stdio, HTTP, and SSE transports. Loads Model Context Protocol servers, exposes their tools to the agent.
  • React TUI (Ink-based): live token meter in the footer, tool execution display, full slash-command palette.
  • Slash commands: /memory (inspect), /models (setup), /rewind (checkpoint), /help, /plan, /act, /skills.

install

# clone and install the launcher
git clone https://github.com/tashfeenahmed/ob1.git
cd ob1 && ./scripts/install.sh

# or compile a self-contained binary
./scripts/install.sh --binary

# then, in any project
cd ~/code/my-project
ob1

one binary. zero runtime deps. reads your repo, writes code you approve.