Developer Tools●●Solid
A human-curated, CLI-driven Context Layer for AI agents
Human-curated context beats auto-RAG, but folders-as-context is a solved workflow pattern.
CozyShip It
anatoliikmt
203mo ago
Back to browse
GitHub Repository
Agent-first intent and constraint tracking layer for Git. Structured, queryable memory for AI coding agents.
33 starsRust
Telos – A structured context framework for humans and AI agents
by wrencanfly·Feb 28, 2026·3 points·0 comments
AI Analysis
●●●BangerBig BrainZero to OneBold Bet
Git for the 'why': intent DAG alongside code DAG, built for AI agents.
Strengths
- •Genuine architectural insight: AI agents need persistent context Git can't provide (reasoning, constraints)
- •Content-addressable design mirrors Git's proven approach; natural MCP integration point for Claude/other agents
- •Solves real cross-session context recovery problem for agentic workflows
Weaknesses
- •Adoption risk: requires discipline to populate intents/constraints; friction if not integrated into IDE workflow
- •Early-stage implementation; unclear how it scales with codebase size or team adoption friction
Category
Target Audience
AI-assisted development, teams with complex architectural history, LLM coding assistants needing persistent context
Post Description
Telos is a structured intent and decision tracking layer that works alongside Git. It doesn't replace Git — it captures the why behind code changes in a queryable, machine-readable format.
Git tracks what changed in your code. Telos tracks what you intended, what constraints you set, and what decisions you made and why. Every intent, decision, and behavioral expectation is stored as a content-addressable object (SHA-256), forming a DAG that mirrors your development history.
Telos is designed for both human developers and AI agents. Its --json output mode and context command make it a natural integration point for LLM-powered coding assistants that need to recover project context across sessions.
Similar Projects
Developer Tools●●●Banger
Hivemind – A shared coordination layer for AI agents
Shared state for AI agents that actually prevents duplicate work and token waste.
Solve My ProblemShip ItBig Brain
gbram
103mo ago
Developer Tools●●Solid
Kster.ai – Structured product context your coding agent reads over MCP
MCP integration for product context when Cursor already handles code context.
Big BrainShip It
catalinviciu
304d ago
Developer Tools●●Solid
ai11y – A structured UI context layer for AI agents
The describe → plan → act split is an elegant, accessibility-inspired way to give LLM agents actionable UI context: annotate with data-ai-* attributes or use the Marker component, call describe(), send it to a planner, then client.act() executes DOM instructions. It's a clever middle layer that turns messy DOM state into structured inputs for server-side planning, though adoption will hinge on robust selector semantics and out-of-the-box integrations with popular LLMs and automation backends.
Big BrainNiche Gem
maerzhase3000
114mo ago
Developer Tools●●●Banger
Hopsule – Persisten Memory Layer for AI Engineering
Decision memory with enforceable context beats Cursor's built-in context features.
Big BrainSolve My Problem
firatcan
513mo ago
AI/ML●●Solid
Agentic Intent Benchmark
First benchmark testing structured requirements on complex greenfield agent tasks.
Niche GemBig Brain
ryan4rtmx
2022d ago