Radar / AI infrastructure / TokenForge
TokenForge: context-window optimization layer for AI coding agents
A JavaScript middleware that cuts coding-agent token spend by sandboxing tool output (claimed 98% reduction), persisting session memory in SQLite with full-text search, and routing across 17 model platforms via MCP and hooks.
Why it matters
It attacks the biggest cost driver of agentic coding head-on: tool-call output that floods context windows. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI instead of locking to one harness.
What you could build with it
An indie developer running Claude Code or OpenCode on a tight API budget could place TokenForge in front of their agent to compress noisy tool-call output and carry session memory across restarts, cutting token spend on long refactors while the agent keeps working with the same context.
Does it hold up?
Too early to judge — created today with 30 stars; the 98% reduction claim is README-only with no published benchmark, and no license is declared in the repo.
Learn more
First spotted on github: source.
More AI infrastructure
DeepGEMM: DeepSeek's open GPU BLAS kernel libraryDeepSeek's DeepGEMM, a clean and efficient open-source BLAS kernel library for NVIDIA GPUs (up to 1550 TFLOPS on…infra · JEV 0.77OpenViking — self-evolving context database for AI agentsByteDance Volcengine's open-source (AGPL-3.0) context database that unifies agent memory, knowledge RAG, and skills…infra · JEV 0.76Modular open-sources MAX inference server, Mojo stdlib and accelerator kernelsThe core of Modular's unified AI deployment stack is now open: the MAX inference server (OpenAI-compatible endpoints)…infra · JEV 0.76OmniRouteFree MIT AI gateway: one endpoint, 290+ providers and 500+ models with quota-aware auto-fallback.infra · JEV 0.75Context Mode: context-window optimization for AI coding agentsMCP server for AI coding agents that sandboxes verbose tool output and persists session memory, cutting context use by…infra · JEV 0.74StrataOpen-source inference engine that runs the 125B-parameter Qwen3.8-Flash-Next MoE on a single consumer GPU with 12GB+…infra · JEV 0.74
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.