SigMap v8.9: Deterministic Context Layer Cuts Token Use 97% for AI Coding Agents
SigMap v8.9 is a deterministic, verifiable grounding layer for AI code work. It claims a 97.0% token reduction, 87.8% hit@5 retrieval accuracy (vs 13.6% random), and 49.2% fewer prompts per task (1.44 vs 2.84). The tool is zero-dependency, fully offline, and works with TypeScript, Python, Go, Rust, Java, Kotlin, Ruby, PHP, Swift, C#, C++, Dart, Scala, Vue, Svelte, GraphQL, SQL, Terraform, R, GDScript, and more.
Core workflow: ask, validate, judge, learn
The workflow goes beyond simple context shrinking:
- Generate a compact signature map once with
npx sigmap. - Ask for files specific to the current task:
sigmap ask "explain the auth flow". This outputs a ranked file list and.context/query-context.mdready to paste. - Validate coverage:
sigmap validate --query "auth login token"checks if context is sufficient. - Judge grounding:
sigmap judge --response response.txt --context .context/query-context.mdscores whether the answer is grounded in the code.
MCP and IDE integration
SigMap is MCP-ready and works with Copilot, Claude Code, Cursor, Windsurf, Codex, OpenCode, and Gemini CLI. The v8.9.1 release adds a squeeze_output MCP tool and squeeze --response CLI flag to compress noisy stack traces, CI logs, or JSON payloads deterministically mid-session — the 19th MCP tool.
Benchmark results
Latest saved benchmark (v8.9.1, July 2026):
| Metric | Without SigMap | With SigMap |
|---|---|---|
| Task success proxy | 10% | 67.8% |
| Prompts per task | 2.84 | 1.44 |
| Retrieval hit@5 | 13.6% | 88% |
| Overall token reduction | — | 97.0% |
| GPT-4o overflow repos | 16/21 | 0/21 |
Performance spans 21 repos and 90 real coding tasks.
Quick start
npx sigmap
sigmap ask "explain the auth flow"
# Outputs ranked file list + .context/query-context.md
# Paste context into AI assistantFor teams or CI, SigMap offers configurable strategies and generalization for monorepos. It also has a dedicated guide for open-source agents (OpenCode, Aider, Cline) and local LLMs (Ollama, llama.cpp, vLLM) — zero cost, full privacy.
📖 Read the full source: HN LLM Tools
👀 See Also
Engram: Hybrid Memory Plugin for OpenClaw Agents — Vector + Semantic Search with Decay
Engram gives OpenClaw agents persistent memory across sessions using SQLite+FTS5 for exact recall and LanceDB for semantic search, with decay classes and auto-capture hooks.
Building a Persistent AI Knowledge Infrastructure with OpenClaw
A developer built 'Brain'—a central knowledge service with local RAG, multi-agent coordination, and a typed plugin system—to solve the statelessness problem in AI setups. The system runs entirely on local hardware using Ollama, Postgres, MongoDB, Qdrant, and Memgraph.
Free pharmacovigilance signal detection tool built with Claude Code
A developer used Claude Code to build a free pharmacovigilance platform that analyzes 2.9 million FDA adverse event reports, running statistical signal detection that commercial platforms charge $50K-500K/year for. The tool is hosted for free on HuggingFace.
PocketBot: iOS app uses Claude to generate deterministic JavaScript automations from natural language
PocketBot is an iOS mobile automation app that uses Claude via AWS Bedrock to convert plain-language requests into self-contained JavaScript scripts. The LLM writes the code once, then the deterministic scripts run on schedule in a sandboxed runtime without AI involvement.