open source

6 articles

← All topics

Headroom: open-source token compression for AI agents
headroomai-agentstoken-optimizationcontext-compressionmcp+13

On 2026-06-22, the open-source project Headroom shipped v0.27.0, a release that adds `headroom update`, `headroom doctor`, and a hot-reload path for live proxy env knobs. The repository (headroomlabs-ai/headroom on GitHub) reached 48,803 stars, 3,406 forks, and 368 open issues on 2026-06-24, six months after its first commit on 2026-01-07. The project compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach an LLM, with published benchmarks of 92% token reduction on code search, 92% on SRE incident debugging, 73% on GitHub issue triage, and 47% on codebase exploration. Accuracy on GSM8K, TruthfulQA, SQuAD v2, and BFCL is preserved or improved. Headroom is Apache 2.0 licensed, runs locally, and exposes a library, a proxy, an agent wrapper, and an MCP server. v0.27.0 also adds `headroom mcp install`, tabular `.xlsx/.xls` compression, and Cortex Code (Snowflake CoCo) to the supported agent list.

caveman: Julius Brussee's terse-output skill
open-sourcetypescriptclaude-codecodexgemini+21

GitHub repo JuliusBrussee/caveman — a TypeScript Claude Code / Codex / Gemini / Cursor skill that asks the agent to talk like a caveman. 74,940 stars and 4,230 forks as of 2026-06-20, MIT, 15 releases (latest v1.9.0 on 2026-06-12). Project-published benchmark of 10 real Claude API prompts shows 65% average output-token reduction (range 22–87%); caveman-compress sub-skill cuts 46% of tokens from real memory files. The README's own Important box is the lead caveat: caveman only affects output tokens — thinking/reasoning tokens are untouched.

crewAI: Multi-Agent Orchestration at 53K GitHub Stars
open-sourcecrewaimulti-agentorchestrationpython+6

MIT repository (crewAIInc/crewAI) with 53,499 stars and 7,488 forks as of June 14, 2026. Crews+Flows architecture, 14.27M PyPI downloads in the last month, stable release 1.14.7 from June 11, 2026. Anonymous telemetry active by default, opt-out via OTEL_SDK_DISABLED. Risk of unpredictable token costs and autonomy without documented guardrails. Main sources: GitHub repo and docs.crewai.com.

Instructor: Pydantic Structured Outputs for LLMs
open-sourcepythonpydanticstructured-outputsllm+6

MIT Python library (567-labs) for extracting validated JSON from any LLM via Pydantic models. 13.2k stars, 1.1k forks, v1.15.1 with Bedrock SSRF fix, support for OpenAI, Anthropic, Gemini, Cohere, Ollama, Bedrock, and 15+ other providers. v1.15.2 (May 10, 2026) adds sensitive log redaction.

smolagents: Hugging Face Agents Code in Python, Not JSON
huggingfacesmolagentsagentcode-agentopen-source+5

The Hugging Face library for building LLM agents where actions are executable Python snippets, not JSON dictionaries. 27.8k stars, Apache 2.0, latest release v1.26.0 from May 29, 2026. Mandatory sandbox for code execution.

didilili/ai-agents-from-zero: Chinese MIT AI Agent Guide
open-sourcelangchainlanggraphmcprag+6

MIT Chinese repository (Datawhale) with 27 chapters on LangChain, LangGraph, MCP, RAG, Skills, and fine-tuning. 1,914 stars, 254 forks, two completed projects as of May 2026. Language barrier explicitly acknowledged.