Caveman 1.0.0 released
First stable release requiring caveman-sdk 1.2.0 or later, with comprehensive adapter support and error handling improvements.
What changed in 1.0.0
- Refused retrieval calls now return error codes and allow execution to continue instead of failing.
- Wrapping clients multiple times runs a single Caveman layer instead of stacking, and Google clients are never mutated or closed.
- Version compatibility checks warn when frameworks are outside tested ranges; override with accept_framework_version=True.
- Adapters for Anthropic Bedrock, Vertex, OpenAI 3.x, and LiteLLM Router added; histories are budgeted at 2 MiB with image hashing.
- Invalid recovery arguments and missing cancel signals are handled gracefully across OpenAI, Anthropic, and MCP adapters.
Check before you update
- License changed from MIT to Apache-2.0.
Summarised by AgentGid from JuliusBrussee's official release notes on GitHub, as reported there; read the original before relying on it. Price, status and release dates come from our daily data.
Caveman at a glance
| What it is | Skill, local proxy and SDK that reduce the tokens coding agents write and read: the skill makes replies terse and the proxy compresses logs, JSON, test output and web pages before they reach the model. It works with Cla… |
|---|---|
| Latest version | 4.1.0, Nov 8, 2026. This page is about an earlier release. |
| Release pace | 5 stable releases in the last 30 days; 1.0.0 came the same day as the previous one |
| Price | Free + $300/mo. Caveman agent and SDK are free and open source (Apache-2.0). Caveman Cloud Free tier is $0/month for one person with usage allowances (100K events, 600 agent minutes, 25K routing … Official pricing ↗ (checked Oct 14, 2026) |
| Gid Score | 31 #41 in Agent tooling for cost, context and memory |