Mibayy/token-savior
MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine. Works with every MCP client.
Proof-of-Time attestation — Ed25519-signed timestamps with multi-source corroboration and explicit error bounds. IETF draft-helmprotocol-tttps
Appears on
Quick read
Latest capture 2026-08-24 03:07
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
7 observed captures since 2026-05-23. Observed captures are shown by default.
Stars from first capture +1
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine. Works with every MCP client.
Tessera — Memory layer for every AI. 58 MCP tools, 54 REST endpoints, local-first, AES-256 encrypted.
Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.
Pre-execution governance for AI agents. Sub-millisecond tool call validation, drift detection, circuit breakers, human-in-the-loop holds. 829 tests. 56 MCP tools.
A command center for AI coding agents — run Claude, Gemini & Codex in parallel, each in its own git worktree
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.