mksglu/context-mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Transparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server and persist traces to SQLite, Postgres or MySQL.
Appears on
Quick read
Latest capture 2026-11-05 09:39
Compare the starting count and capture dates, not just the percentage. How to read GitHub star growth. Missing history is not zero growth.
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
10 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Claude Code 9
Explore indexed repositories with these instruction or planning files. File detection is not a quality, compatibility, or safety assessment; check the actual instructions upstream.
AGENTS.md, CLAUDE.md, and GEMINI.md searches also match nested paths. Other file searches require the exact repository-root path. To require several files, select them together in the search filters.
1 observed capture since 2026-11-05. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Remote approvals, policy checks, and execution evidence for unattended AI agents.
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Open source local terminal cli with any LLM
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
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.