Alternatives
Products that do what Caveman does
why use many token when few do trick
- 1
- 2
- 3
Prompt injection and token savings - #1 in benchmarks
Jul 2026 · constellationgate.ai
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11RA
Hey HN! I've been building Claurst - a clean-room implementation of Claude Code in Rust, with extra features to make my ideal agentic Open-Source AI CLI. It's WIP and rough, but I'm shipping a lot to make it amaze amaze amaze. Inspired by this HN post [1] I saw a few hours ago about caveman speak for token-efficient output, I added /Caveman and /Rocky (from project Hail Mary) to Claurst. Caveman grammar drops ~70% of output tokens keeping technical substance and Rocky brings a close compression with more personality. Both are first-class slash commands with three levels: lite,…
Apr 2026 · github.com
- 12HN
I built Hydra because I kept losing my flow when Claude Code hit usage limits mid-task. I would copy context, open another tool, and then re-explain everything. This would be super annoying for me. Hydra wraps your AI coding CLIs (Claude Code, Codex, OpenCode, Pi, or any terminal-based tool) in a single command. It monitors terminal output for rate limit patterns, and when one provider runs out, you switch to another with one keypress. Your conversation history, git diff, and recent commits are automatically copied to your clipboard so you can paste and keep going. The fallback chain is…
Apr 2026 · github.com
- 13SC
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality. So we built Semble. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and…
May 2026 · github.com
- 14LA
LunaRoute is a high-performance local proxy for AI coding assistants like Claude Code, OpenAI Codex CLI, and OpenCode. Get complete visibility into every LLM interaction with zero-overhead passthrough, comprehensive session recording, and powerful debugging capabilities. - See Everything Your AI Does - get full logs (JSONL), summary of sessions including tokens used (input/output) as well as tools usage and success rates. - Privacy & Compliance Built-In - redact or tokenize any sensitive information (regex based). - Speaks OpenAI and Anthropic dialects so you can route (and translate)…
Oct 2025 · github.com
- 15TT
I use Claude Code, Codex and Cursor (and sometimes Antigravity) basically every day, and could never tell how much I was actually consuming across all of them. So I built TokenMaxxer. A small CLI reads the files these tools already write locally and puts it all in one dashboard, broken out by tool, model, provider and day. It covers 18 tools now, and you get a profile page with your daily activity, cost estimates, and your top models and tools. There's also a global leaderboard if you want to compete against other TokenMaxxers! I'd love to see if anyone can beat the first place (currently…
Aug 2026 · tokenmaxxer.xyz
- 16
- 17OS
We built an open-source library of 125 GTM (go-to-market) skills that plug into AI coding agents like Claude Code, Codex, and Cursor. With these skills an AI agent can automatically: - Find ICP leads from conference speakers, LinkedIn activity, or job boards - Generate personalized cold email sequences - Monitor competitor blogs, pricing pages, and hiring signals - Generate programmatic SEO pages from keyword lists - Track where your brand appears in ChatGPT, Perplexity, and Claude answers --- How skills work Each skill is a structured markdown file containing instructions, scripts, and tool…
Mar 2026 · github.com
- 18OS
Hi HN, Matvey, Ildar, Joey, and Dominik here. If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools. We were too, and found that solutions like prompt-based filtering or secondary "guard" LLMs can be unreliable. Our thesis is that agent security should be handled at the network level between the agent and the LLM, just like a traditional web application firewall. So we built Archestra Platform: an open-source gateway that acts as a secure proxy for your AI agents. It's designed to be a deterministic firewall against…
Oct 2025 · archestra.ai
- 19DG
I got frustrated watching Claude Code fail at using modern APIs (ask it about GPT-5 and it says it doesn't exist). Existing solutions like Context7 dump thousands of tokens of irrelevant docs into context. So I built DeepCon. How it works: - Crawled 10,000+ official docs using agentic browser automation and structured them hierarchically - Query decomposer breaks down requests, searches in parallel, then merges only relevant context - Returns just what's needed: 2.4x fewer tokens than Context7 Results on our benchmark: DeepCon achieved 90% accuracy vs Context7's 65% on real-world tasks with…
Nov 2025 · deepcon.ai
- 20PR
Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch/transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!
Dec 2025 · github.com
- 21
- 22AR
Hi HN. I'm the founder of Phoenix Labs (ex TikTok, Applied AI) and we're open sourcing our internal tooling today which is like a toolchain / meta-harness for CLI agents useful for really scaling eng and creative work. We are a very small team who's building a very ambitious product so we had to find ways to squeeze every ounce of efficiency that we could get our hands on. Harness strengths of different models (Claude, GPTs) and CLI-harnesses (Claude Code, Codex), safe/robust browser integration to speed up UX/QA testing, teams cli to speed up security reviews and parallelize…
May 2026 · agents-cli.sh
- 23OA
I've been running Claude Code and Codex together every day. At some point I figured out you can use tmux to let them talk to each other, so I started doing that. Once they could coordinate, I kept adding more agents. Before long I had a whole team working together. But any time I rebooted my machine, the whole thing was gone. Not just the tabs. The way they were wired up, what each one was doing, all of it. Nothing I'd found treats your agent setup as a topology, as something with a shape you can save and bring back. So I built OpenRig, a multi-agent harness. A harness wraps a model. A "rig"…
Apr 2026 · github.com
- 24SM
I built this because I got tired of watching Claude Code read through massive files just to find a few functions. Sourcerer lets AI agents search code semantically and grab exactly the code chunks they need instead of burning tokens on whole files. It uses tree-sitter to parse your codebase and creates a searchable index. So instead of "read auth.py (538 lines)", an agent can search for "user authentication logic" and get back just the relevant functions. Demo: https://asciinema.org/a/736638 GitHub: https://github.com/st3v3nmw/sourcerer-mcp
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →