DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: Tokencap – Token budget enforcement across your AI agents
I built this after hitting the same wall repeatedly — no good way to enforce token budgets in application code. Provider caps are account-level and tell you what happened, not what is happening.<p>Two ways to add it:<p><pre><code> # Direct client wrapper client = tokencap.wrap(anthropic.Anthropic(), limit=50_000) # LangChain, CrewAI, AutoGen, etc. tokencap.patch(limit=50_000) </code></pre> Four actions at configurable thresholds: WARN, DEGRADE (transparent model swap), BLOCK, and WEBHOOK. SQLite out of the box, Redis for multi-agent setups.<p>One design decision worth mentioning: tokencap tracks tokens, not dollars. Token counts come directly from the provider response and never drift with pricing changes.<p>Happy to answer any questions.
Tokencap addresses a legitimate pain point in AI development—preventing runaway costs at the application level—with a developer-friendly implementation. However, it currently lacks traction and faces significant competition from established observability tools and LLM gateways that are likely to incorporate similar features.