ZeroBurn – Cut coding-agent token burn 98% with 0-token MCP and local Ollama The team behind directly.social released ZeroBurn v2.6.0, an open-source toolkit it says cuts cloud token consumption in AI coding-agent loops by up to 99.1% — from 84,947 tokens to 724 tokens per single agent loop, and from roughly 339,788 to 2,896 billed tokens across five turns — by replacing cloud calls with 0-token static AST checks, local Ollama diff review, code-graph pre-fetching and 1-line test receipts. In a benchmark run on a 1,465-file repository, ZeroBurn reported a 96.7% reduction in repo and route discovery tokens (15,429 to 512), 99.7% in rule and docs ingestion (59,202 to 195), 99.8% in test verification logs (6,816 to 17) and 100% in diff security audit (3,500 to 0), with the local qwen2.5-coder:14b audit completing in 8.92 seconds. The tool installs via a git clone of the .agents directory and an init script that auto-detects the stack and resolves installed local Ollama models. Cut AI coding-agent token & quota burn by 70–83% with 0-token static & blast-radius checks, dynamic local Ollama diff review + Judgment Kernel failure digests, code-graph pre-fetching, parallel swarm file leases, and 1-line test receipts — without sacrificing Contract-First TDD or strict quality gates. Engineered by the team building directly.social https://directly.social @directlysocial . Option A — Try it live in your own repo right now Zero Install : Paste this 1-liner inside any Git repository on your machine to see your exact discovery token savings and run a real-time 0-cloud-token Static AST + Local Ollama Diff Audit on your current git diff : curl -fsSL https://raw.githubusercontent.com/thoufeeque22/zeroburn/main/benchmarks/try-now.mjs | node Option B — Install ZeroBurn into your project 1 Command : Clones .agents/ , auto-detects your stack Next.js , TypeScript , Prisma , dynamically resolves your installed local Ollama models "auto" , and configures 1-line quiet-cli verification: git clone https://github.com/thoufeeque22/zeroburn /tmp/zb && cp -R /tmp/zb/.agents . && rm -rf /tmp/zb && node .agents/scripts/init.mjs --pull View raw ASCII tabular output from a 1,465-file repository 🔥 ZeroBurn v2.6.0 — Live Token-Savings Benchmark & 0-Token Diff Auditor 📂 Repository: /Users/dev/my-app branch: feat/billing-quota 📊 1. Context & Cloud Token Footprint Standard Subagent vs ZeroBurn ┌────────────────────────────┬────────────────────────────┬─────────────────────────────┬────────────────┐ │ Pipeline Stage │ Vanilla Agent │ ZeroBurn v2.6.0 │ Cloud Saved │ ├────────────────────────────┼────────────────────────────┼─────────────────────────────┼────────────────┤ │ 1. Repo & Route Discovery │ 15,429 tok 1465 files │ 512 tok 5-line digest │ -96.7% │ │ 2. Rule & Docs Ingestion │ 59,202 tok 4348 lines │ 195 tok 7-line digest │ -99.7% │ │ 3. Test Verification Logs │ 6,816 tok verbose log │ 17 tok 1-line quiet-cli │ -99.8% │ │ 4. Diff Security Audit │ 3,500 tok Cloud Pro │ 0 tok Local Ollama + AST │ -100.0% │ ├────────────────────────────┼────────────────────────────┼─────────────────────────────┼────────────────┤ │ TOTAL Single Agent Loop │ 84,947 cloud tokens │ 724 cloud tokens │ -99.1% │ │ 5-TURN CUMULATIVE BILLING │ ~339,788 billed tokens │ ~2,896 billed tokens │ 336,892 saved │ └────────────────────────────┴────────────────────────────┴─────────────────────────────┴────────────────┘ 🛡️ 2. Live 0-Cloud-Token Diff Audit HEAD~1..HEAD — 3 changed file s ┌────────────────────────────┬──────────┬──────────────┬─────────────────────────────────────────────────┐ │ Audit Engine │ Time │ Cloud Cost │ Verdict │ ├────────────────────────────┼──────────┼──────────────┼─────────────────────────────────────────────────┤ │ Static AST & Modularity │ 0.01s │ 0 cloud tok │ ✅ PASS <=200L, 0 any , line-1 actions │ │ Ollama qwen2.5-coder:14b │ 8.92s │ 0 cloud tok │ ✅ PASS — Clean diff verified │ └────────────────────────────┴──────────┴──────────────┴─────────────────────────────────────────────────┘ Most multi-agent setups "PM / Architect / Dev / QA prompt packs" drain your 5-hour and weekly Claude / Gemini usage limits in two tickets because: 1. Blank-Slate Subagent Tax: Every subagent starts fresh and wastes 3–5 turns re-reading markdown rule files, directory trees, and full source files. 2. Test Log Bloat: Verbose test/lint runs vitest , eslint , tsc dump 500+ lines ~15,000 tokens into context on every turn, which then gets re-billed on every subsequent turn $O N^2 $ context growth . 3. Frontier Models on Mechanical Checks: Cloud pro / Opus models are spawned to check line counts, any types, and file blast radius that Python + local Ollama can verify in 0 cloud tokens . Measured on a real feature/audit loop "Locate and audit checkUploadQuota tier logic, run all 6 billing unit test suites 70 tests , and execute a diff security audit" . Full raw traces and reproducible runner in benchmarks/REAL WORLD BENCHMARK.md https://github.com/thoufeeque22/zeroburn/blob/main/benchmarks/REAL WORLD BENCHMARK.md : | Stage | Standard Coding Agent Vanilla | zeroburn v2.6.0 Engine | Measured Savings | |---|---|---|---| | 1. Repo & Route Discovery | find src -type f 1,470 lines / 15,454 tokens | build repo map digest 6 lines / 636 tokens : 28 Prisma models, 32 domains, 60 API routes | -95.9% tokens | | 2. Governance & Rule Loading | cat .agents/AGENTS.md .agents/base/ .md 276 lines / 10,274 tokens | Pre-computed inlined rule digests 7 lines / 195 tokens | -98.1% tokens | | 3. Symbol Localization | grep -rn "quota" src/lib/ 64 matches / 1,921 tokens + exploratory reads | codebase-memory-mcp search graph - FreemiumGuard.checkUploadQuota src/lib/billing/freemium-guard.ts:43-83 in 0 LLM tokens | -100% exploratory LLM tokens | | 4. Unit Test Run 6 suites, 70 tests | npx vitest run 243 lines / 6,816 tokens per run | node .agents/scripts/quiet-cli.mjs unit 1 line / 17 tokens | -99.75% test log tokens | | 5. Diff Security & Quality Audit | Cloud Pro / Opus subagent review ~12,000+ cloud tokens | 0-token Python AST/Blast-Radius + Local Ollama qwen2.5-coder:14b-custom 13.43s , 0 cloud tokens | 100% cloud audit quota saved | | Single-Pass Overhead Total | 46,465+ Cloud Tokens | 848 Cloud Tokens | 98.2% Reduction | ❌ WITHOUT ZEROBURN Standard Subagent — 46,465 tokens burned before writing code : $ find src -type f 1,470 lines 15,454 tokens $ cat .agents/AGENTS.md .agents/base/ .md 276 lines 10,274 tokens $ grep -rn "quota" src/lib/ 64 lines 1,921 tokens $ npx vitest run src/ tests /unit/ billing 243 lines 6,816 tokens $ Spawns Cloud Pro Subagent for Diff Review 12,000 tokens ---------------------------------------------------------------------------------- 💥 Result: 46,465+ tokens & ~185,000 cumulative billed tokens across a 5-turn loop. ✅ WITH ZEROBURN v2.6.0 848 tokens — 98.2% reduction : $ codebase-memory-mcp search graph "billing tier quota check" 0 tokens - FreemiumGuard.checkUploadQuota src/lib/billing/freemium-guard.ts:43-83 $ Inlined REPO MAP DIGEST + Rule Digests 831 tokens - 28 Prisma Models | 32 src/lib domains | 60 API Routes $ node .agents/scripts/quiet-cli.mjs unit src/ tests /unit/ billing - quiet-cli unit: PASS Test Files 6 passed 6 , Tests 70 passed 70 17 tokens $ parallel-audit.py Python AST + Local Ollama qwen2.5-coder 0 cloud tokens ---------------------------------------------------------------------------------- ⚡ Result: 848 tokens total. Surgical edit on Turn 1. Zero cloud Pro audit burn. 1. Single Declarative Config & Dynamic Local Model Resolution .agents/project.config.json : Set "localCoderModel": "auto" and "localProseModel": "auto" to automatically detect and use whichever coder qwen -coder , deepseek-coder , codellama , starcoder and prose gemma , llama , mistral , phi models are installed in local Ollama — or pin specific tags per repo. 2. Auto-Start & Fail-Closed Local Ollama Gate session-start.mjs & workflow common.py : - Automatically starts ollama serve in the background if 127.0.0.1:11434 is down, dynamically resolves installed models from /api/tags , and hard-stops workflows only if no local model is reachable. 3. Automatically starts 4. 0-Token Knowledge Graph Pre-Fetch codebase-memory-mcp : - Pre-fetches top symbol coordinates file:start-end before Discovery and 2-hop impacted call-graph nodes detect changes before Audit in 0 LLM tokens . 5. Pre-fetches top symbol coordinates 6. Inlined Rule Digests & Dynamic REPO MAP DIGEST : - Pre-computes Prisma models, src/lib/ domains, Server Actions, and /api/ endpoints in <5ms Python and inlines compressed rule digests so subagents never waste turns calling read file on markdown docs. 7. Pre-computes Prisma models, 8. Pool-Safe FALLBACK CHAINS & <= 4 Handoff Cap: - Steps down through cheaper 5-hour tiers pro - flash - flash lite - inherit before touching inherit , protecting weekly reserve model pools while keeping Track M pipelines under the 4-handoff cliff. 9. Steps down through cheaper 5-hour tiers 10. Quiet CLI Verification + Local Ollama Judgment Kernel node .agents/scripts/quiet-cli.mjs